© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15055
    Prev
    Next
    INDEX
    Explanations

    text with a numerical identifier, someone doing the voicing, job and bad answers

    oai_token-act-pair · gemini-2.0-flash

    voiced characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     veja
    -0.45
    <bos>
    -0.44
    ContentAsync
    -0.43
     Miocene
    -0.43
     TTS
    -0.43
     GQ
    -0.42
     vejo
    -0.42
    aways
    -0.41
     tts
    -0.41
     aapt
    -0.41
    POSITIVE LOGITS
    GEBURTSDATUM
    0.69
    URLException
    0.64
    ReusableCell
    0.63
     يتيمه
    0.63
    ValueStyle
    0.56
    انجليز
    0.56
    SPATH
    0.55
     Taktlose
    0.55
    RenderAtEndOf
    0.54
    GRANTED
    0.51
    Activations Density 0.411%

    No Known Activations