© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1910
    Prev
    Next
    INDEX
    Explanations

    code snippets related to XML parsing and bash scripting for file handling

    oai_token-act-pair · gemini-2.0-flash

    French/code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     nevoie
    -0.59
    uppertal
    -0.58
    umque
    -0.58
    omenclature
    -0.55
     quæ
    -0.54
    apatalk
    -0.54
    føl
    -0.53
    슷
    -0.53
    تفصیلات
    -0.53
     الوطنيه
    -0.52
    POSITIVE LOGITS
     Процитовано
    0.69
    windowFixed
    0.60
    ChildScrollView
    0.57
    CloseOperation
    0.56
     BorderSide
    0.52
     cref
    0.52
    ()");
    0.51
     ?></
    0.51
     EO
    0.49
    SizeF
    0.49
    Activations Density 2.021%

    No Known Activations