© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13773
    Prev
    Next
    INDEX
    Explanations

    items contained inside of lists or enumerated categories

    oai_token-act-pair · 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
    তথ্যসূত্র
    -0.55
     kaynağından
    -0.50
    atau
    -0.46
     kasarigan
    -0.45
    principalColumn
    -0.42
    ugno
    -0.40
     gaun
    -0.40
    PyTuple
    -0.40
    __).
    -0.40
     Италијани
    -0.40
    POSITIVE LOGITS
     كومونز
    0.59
     števil
    0.56
    ská
    0.56
    jsdelivr
    0.54
    getRuntime
    0.54
    väg
    0.53
    ův
    0.53
    istical
    0.51
     $_"
    0.51
     Krá
    0.50
    Activations Density 32.642%

    No Known Activations