© 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. 16026
    Prev
    Next
    INDEX
    Explanations

    a mix of percentages related to measurement and words from what appears to be a Slavic language

    oai_token-act-pair · gemini-2.0-flash

    two-letter country codes

    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
    ORETICAL
    -0.67
     NDEBUG
    -0.66
     RISERV
    -0.62
     TAMBÉM
    -0.57
     HIEROGLYPH
    -0.56
     COMPOUNDS
    -0.55
    SourceChecksum
    -0.54
     TÉCNICA
    -0.54
     CALIFORNI
    -0.54
    Bibliograf
    -0.53
    POSITIVE LOGITS
     SC
    0.84
     SP
    0.82
     ES
    0.81
     TR
    0.81
     AR
    0.81
     PE
    0.80
     GL
    0.79
     PA
    0.79
     AF
    0.78
     SE
    0.78
    Activations Density 4.006%

    No Known Activations