© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8094
    Prev
    Next
    INDEX
    Explanations

    financial reports or forecasts

    oai_token-act-pair · gemini-2.0-flash

    business/finance texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    setDuration
    -0.58
    FED
    -0.54
    ABAJO
    -0.53
    SourceChecksum
    -0.50
    posedge
    -0.50
     Long
    -0.47
    Fed
    -0.46
     Fed
    -0.46
    ilidad
    -0.45
    ubung
    -0.44
    POSITIVE LOGITS
    Diweddarwch
    0.56
    Xna
    0.55
     sympathies
    0.54
    rzost
    0.52
    ituaries
    0.51
     tqdm
    0.50
     Савезне
    0.49
    isalpha
    0.49
    providedIn
    0.49
    Билгалдахарш
    0.49
    Activations Density 0.561%

    No Known Activations