© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10318
    Prev
    Next
    INDEX
    Explanations

    clauses where someone is stating their opinion on a subjective matter

    oai_token-act-pair · gemini-2.0-flash

    Foreign 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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    parsedMessage
    -0.67
    )))));
    -0.63
    +#+
    -0.59
     NUKAT
    -0.58
    ListItemIcon
    -0.57
     getCode
    -0.56
    PositiveButton
    -0.56
     setCode
    -0.55
    ArgsConstructor
    -0.54
    ^(@)
    -0.53
    POSITIVE LOGITS
    føre
    0.50
    føring
    0.46
    lib
    0.46
     poveznice
    0.46
    듈
    0.45
    liculas
    0.45
     Commencez
    0.45
     ImportError
    0.45
     skjer
    0.44
     ajutor
    0.44
    Activations Density 0.657%

    No Known Activations