© 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. 13823
    Prev
    Next
    INDEX
    Explanations

    hexadecimal code and related terms, possibly from a font file

    oai_token-act-pair · gemini-2.0-flash

    0

    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
     AF
    -1.13
     SM
    -1.11
     SA
    -1.09
     SR
    -1.09
     ES
    -1.08
     SC
    -1.08
     PA
    -1.07
     DA
    -1.06
     CE
    -1.06
     SP
    -1.06
    POSITIVE LOGITS
    ORETICAL
    0.75
     REACTOR
    0.73
     DOWNVOTE
    0.72
     LABORATOR
    0.63
     RISERV
    0.63
     DETECTION
    0.61
     COMPOUNDS
    0.61
     RECOMMENDATIONS
    0.60
     DEPOSITORY
    0.60
     AIRCRAFT
    0.59
    Activations Density 17.169%

    No Known Activations