© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14510
    Prev
    Next
    INDEX
    Explanations

    words that seem to be the first few letters of a longer word (often proper nouns with some exceptions, possibly abbreviations)

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    aarrggbb
    -0.74
    <bos>
    -0.66
     disambiguazione
    -0.63
    APORE
    -0.57
    SOUNDBITE
    -0.57
    UALA
    -0.55
    AccessorTable
    -0.54
     Wikimedijinoj
    -0.53
    rxjs
    -0.52
    qrstuvwxyz
    -0.52
    POSITIVE LOGITS
     дописавши
    0.56
    ViewImports
    0.53
     muualla
    0.50
    __(/*!
    0.49
     سكانية
    0.44
    TemporalType
    0.41
     typelib
    0.41
    Eksterne
    0.40
    "]();
    0.40
    tvguidetime
    0.39
    Activations Density 0.707%

    No Known Activations