© 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. 6104
    Prev
    Next
    INDEX
    Explanations

    text within parenthesis and also quotation marks in some instances, suggesting it may be attempting to identify supplementary material or some kind of supporting information

    oai_token-act-pair · gemini-2.0-flash

    (

    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
    -0.71
     Efq
    -0.66
     Majefty
    -0.65
     againſt
    -0.63
    siasme
    -0.62
     pleaſure
    -0.61
    expandindo
    -0.60
     Mocking
    -0.60
     becauſe
    -0.59
     myſelf
    -0.59
    POSITIVE LOGITS
    ”
    0.77
    —
    0.68
    .”
    0.64
    ,”
    0.61
    }
    0.57
    LikeLike
    0.57
     –
    0.56
    –
    0.55
    </strong>
    0.54
    ”—
    0.54
    Activations Density 4.195%

    No Known Activations