© 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. 14950
    Prev
    Next
    INDEX
    Explanations

    various seemingly unrelated symbols, terms, and phrases related to frustration, website structure, cancer, and chemistry.

    oai_token-act-pair · gemini-2.0-flash

    Scientific or technical text

    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
     *
    -1.85
     **
    -1.13
     *
    -1.07
     ***
    -0.98
    .*
    -0.95
     $*$
    -0.95
     *,
    -0.93
     *.
    -0.91
     *$
    -0.89
    .**
    -0.88
    POSITIVE LOGITS
    SPATH
    0.75
    usercontent
    0.73
    medriver
    0.70
    SharedDtor
    0.69
    AxisAlignment
    0.67
    RectangleBorder
    0.63
    VersionUID
    0.62
    saraba
    0.62
    ActionCreators
    0.60
    SerializeField
    0.59
    Activations Density 4.508%

    No Known Activations