© 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. 7958
    Prev
    Next
    INDEX
    Explanations

    technical terms, definitions, and formal language used in academic articles and research papers

    oai_token-act-pair · gemini-2.0-flash

    non-english/uppercase words

    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
    SC
    -1.06
    MS
    -1.04
    MP
    -1.02
    CS
    -1.01
    SM
    -1.01
    SS
    -1.01
    SP
    -1.01
    CL
    -0.99
    ES
    -0.98
    AM
    -0.98
    POSITIVE LOGITS
    BATTERY
    0.45
    mặt
    0.44
     solidarité
    0.42
    LOGOUT
    0.42
    THEORY
    0.41
    INTERIOR
    0.41
    FINISH
    0.41
    SUPPORTED
    0.40
    MAXIMUM
    0.40
    INSTALLATION
    0.40
    Activations Density 29.894%

    No Known Activations