© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7553
    Prev
    Next
    INDEX
    Explanations

    mathematical or arithmetic expressions and formulas

    oai_token-act-pair · gemini-2.0-flash

    say "s" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     S
    -0.67
    ScopeManager
    -0.50
     getS
    -0.46
     स
    -0.45
     С
    -0.42
    vstack
    -0.41
     س
    -0.40
    Slf
    -0.39
    ViewFeatures
    -0.39
    ofag
    -0.39
    POSITIVE LOGITS
    s
    2.63
    ses
    1.09
    ся
    1.07
    ات
    1.07
    es
    1.02
    sof
    1.01
    sre
    0.97
    ים
    0.97
    sers
    0.94
    sted
    0.94
    Activations Density 13.903%

    No Known Activations