© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6536
    Prev
    Next
    INDEX
    Explanations

    code or data snippets containing characters like ',' '=', '+', ';', or 'int'

    oai_token-act-pair · gemini-2.0-flash

    commas and quotes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     وتسجيلات
    -0.87
    ensement
    -0.76
    DockStyle
    -0.75
    OOTDTY
    -0.72
    igshid
    -0.70
    writeField
    -0.69
     مشين
    -0.68
    styleType
    -0.66
     doInBackground
    -0.65
     Exactos
    -0.65
    POSITIVE LOGITS
    fra
    0.49
    وسط
    0.48
    Py
    0.45
     opere
    0.44
    Fra
    0.44
    block
    0.41
    ArrayAdapter
    0.41
    Block
    0.40
    py
    0.39
    display
    0.38
    Activations Density 1.282%

    No Known Activations