© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13082
    Prev
    Next
    INDEX
    Explanations

    the word "points" and, to a lesser extent, the word "instant"

    oai_token-act-pair · gemini-2.0-flash

    points

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     points
    -1.91
    points
    -1.58
    Points
    -1.53
     Points
    -1.48
     POINTS
    -1.37
     puntos
    -1.17
    POINTS
    -1.14
     Punkte
    -1.09
     punten
    -1.04
    <bos>
    -0.99
    POSITIVE LOGITS
    ształ
    0.82
     AssemblyCulture
    0.79
     sélections
    0.78
    AccessorTable
    0.77
     Roskov
    0.73
     виправивши
    0.73
     bezeichneter
    0.72
    uticos
    0.68
    最快更新
    0.68
    istible
    0.67
    Activations Density 0.897%

    No Known Activations