© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10547
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and seemingly unrelated words

    oai_token-act-pair · gemini-2.0-flash

    apostrophe

    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
    Geplaatst
    -0.67
     المعيارى
    -0.65
    migrationBuilder
    -0.65
    IsContent
    -0.60
    Externé
    -0.59
    </thead>
    -0.59
    tagHelperRunner
    -0.57
    RenderAtEndOf
    -0.57
     &___
    -0.55
    RRect
    -0.54
    POSITIVE LOGITS
    ioen
    0.48
    Verdana
    0.48
    通販
    0.48
    kula
    0.46
    tieri
    0.46
    ису
    0.46
    _),
    0.44
    InvalidProtocol
    0.44
     "));
    0.44
    gården
    0.44
    Activations Density 5.616%

    No Known Activations