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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6944
    Prev
    Next
    INDEX
    Explanations

    capitalized abbreviations, especially those used in technical writing and medical contexts

    oai_token-act-pair · gemini-2.0-flash

    Scientific language

    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
     propOrder
    -1.00
    ConstraintMaker
    -0.96
    ST
    -0.93
    Personensuche
    -0.93
    NA
    -0.93
    SH
    -0.89
    RA
    -0.88
    AN
    -0.88
     disambiguazione
    -0.88
    AS
    -0.87
    POSITIVE LOGITS
     RISERV
    0.28
     RSITY
    0.27
    GRAFÍA
    0.25
     ERSITY
    0.23
    ERÍA
    0.22
     CALIFORNI
    0.21
     HIEROGLYPH
    0.20
     COMPOUNDS
    0.20
    ABILIDAD
    0.20
     PICTOGRAM
    0.19
    Activations Density 7.385%

    No Known Activations