© 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. 14875
    Prev
    Next
    INDEX
    Explanations

    code snippets and database references

    oai_token-act-pair · gemini-2.0-flash

    underscore

    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
     pleaſure
    -0.66
     houſe
    -0.62
     themſelves
    -0.62
     uſe
    -0.61
     greateſt
    -0.60
     myſelf
    -0.60
     Ohne
    -0.59
     purpoſe
    -0.57
     itſelf
    -0.56
     étoient
    -0.55
    POSITIVE LOGITS
    AddHtmlAttribute
    0.59
    __':
    0.56
    __':
    0.56
    //
    0.53
    matchCondition
    0.52
     AssemblyCulture
    0.52
    Crossref
    0.51
     onPostExecute
    0.51
    httphttps
    0.50
    Aiheesta
    0.50
    Activations Density 1.242%

    No Known Activations