© 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. 4124
    Prev
    Next
    INDEX
    Explanations

    passages about animals, especially crocodiles, and scientific studies.

    oai_token-act-pair · 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
     fit
    -0.42
     vô
    -0.41
     No
    -0.41
     v
    -0.39
    lau
    -0.39
     $
    -0.39
    lä
    -0.38
    stoff
    -0.38
    at
    -0.37
     rangkaian
    -0.37
    POSITIVE LOGITS
     Efq
    1.02
    parsedMessage
    0.99
    LookAnd
    0.91
     Jefus
    0.90
    Personensuche
    0.87
     Pliocene
    0.87
     itſelf
    0.86
     Majefty
    0.83
     InputDecoration
    0.82
    UnsafeEnabled
    0.82
    Activations Density 22.449%

    No Known Activations