© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12041
    Prev
    Next
    INDEX
    Explanations

    the word "and" and the word "bang."

    oai_token-act-pair · gemini-2.0-flash

    legal and personal narratives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     ddelweddau
    -0.70
    medades
    -0.56
    sunter
    -0.56
    lectic
    -0.54
    rinology
    -0.54
    asanjo
    -0.52
    hicule
    -0.51
     "]";
    -0.50
    ?]
    -0.50
    allage
    -0.50
    POSITIVE LOGITS
     Egli
    0.73
    IntoConstraints
    0.66
     duquel
    0.65
    DoubleQuotes
    0.61
     correctes
    0.60
    ConstraintMaker
    0.60
    enumi
    0.57
     realising
    0.57
     perſon
    0.56
    ably
    0.55
    Activations Density 1.299%

    No Known Activations