© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13151
    Prev
    Next
    INDEX
    Explanations

    descriptions of antique silverware

    oai_token-act-pair · gemini-2.0-flash

    Foreign Language & Technical

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    contentLoaded
    -0.68
    IndentedString
    -0.59
    GeneratedCode
    -0.55
     arşivlendi
    -0.55
    BufferException
    -0.54
    uxxxx
    -0.51
    ustes
    -0.50
     disambiguazione
    -0.50
    DllImport
    -0.50
    POSITIVE LOGITS
     calendriers
    0.54
    }],
    0.49
    \{\\
    0.49
    multicolumn
    0.49
    imwrite
    0.45
     Religions
    0.45
    viewtopic
    0.44
     Wiktionnaire
    0.43
    Enfant
    0.43
     étend
    0.43
    Activations Density 3.286%

    No Known Activations