© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13130
    Prev
    Next
    INDEX
    Explanations

    references to computing problems where the writer uses "I" as a grammatical subject.

    oai_token-act-pair · gemini-2.0-flash

    words related to software installation and troubleshooting

    np_token-act-pair-logits · gpt-4o-mini

    Reinstall or disable

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.57
    InlineData
    -0.52
    WriteAttribute
    -0.52
    IonicModule
    -0.46
    帖最后由
    -0.46
    BeginInit
    -0.45
    LITERATURE
    -0.45
    KeySpec
    -0.44
    amaran
    -0.44
    prepareStatement
    -0.43
    POSITIVE LOGITS
    ècie
    0.64
     reinstall
    0.64
     незавершена
    0.63
    awtextra
    0.61
     reinstalled
    0.61
    kloped
    0.60
     disable
    0.60
     disabling
    0.60
     disables
    0.60
     DISABLE
    0.59
    Activations Density 4.050%

    No Known Activations