© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13187
    Prev
    Next
    INDEX
    Explanations

    substrings of code or chemical names

    oai_token-act-pair · gemini-2.0-flash

    met

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    gena
    -0.47
    qui
    -0.43
    esto
    -0.41
     bi
    -0.41
    undi
    -0.40
     Rat
    -0.40
    arat
    -0.40
    ΠΟ
    -0.39
    нен
    -0.39
    eno
    -0.39
    POSITIVE LOGITS
    <bos>
    1.13
    IsContent
    0.77
     فريبيس
    0.73
     كومونز
    0.70
     bezeichneter
    0.67
     myſelf
    0.66
     themſelves
    0.66
     itſelf
    0.64
     himſelf
    0.64
     متعلقه
    0.63
    Activations Density 2.243%

    No Known Activations