© 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. 10306
    Prev
    Next
    INDEX
    Explanations

    the string "va"

    oai_token-act-pair · gemini-2.0-flash

    va

    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
    va
    -2.92
    VA
    -2.03
    Va
    -1.73
     Va
    -1.55
     va
    -1.55
     VA
    -1.39
    vah
    -1.23
    vas
    -1.17
    ва
    -1.13
    vaa
    -1.02
    POSITIVE LOGITS
    出版年
    0.91
    StoryboardSegue
    0.86
    Personendaten
    0.84
    RenderAtEndOf
    0.76
    évaluateur
    0.75
    WriteBarrier
    0.74
    endpush
    0.73
     AssemblyCulture
    0.73
    rrggbb
    0.69
    enumi
    0.69
    Activations Density 0.588%

    No Known Activations