© 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. 5668
    Prev
    Next
    INDEX
    Explanations

    capitalized words, bolded text, racist terms, and the phrase "DO NOT EDIT"

    oai_token-act-pair · gemini-2.0-flash

    Code, disclaimers, and "DO NOT"

    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
     NOT
    -1.74
    NOT
    -1.48
     BUT
    -1.41
     AND
    -1.40
     ALL
    -1.38
     NEVER
    -1.37
     ANY
    -1.36
     BOTH
    -1.34
     ALWAYS
    -1.34
     BEFORE
    -1.34
    POSITIVE LOGITS
    CHARS
    0.60
    IDAE
    0.57
    PERTIES
    0.56
    IFICATE
    0.56
    ArgsConstructor
    0.55
     IBRARY
    0.54
     CHECKBOX
    0.54
    VELOP
    0.53
    IMENTAL
    0.53
    OTHY
    0.52
    Activations Density 5.295%

    No Known Activations