© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10389
    Prev
    Next
    INDEX
    Explanations

    text describing chromatography analysis

    oai_token-act-pair · gemini-2.0-flash

    chromatography

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    mybatisplus
    -0.90
     TextAppearance
    -0.88
    WebServlet
    -0.85
     nakalista
    -0.81
    ErrUnexpectedEOF
    -0.78
     Савезне
    -0.77
    RenderAtEndOf
    -0.75
    ScopeManager
    -0.74
     виправивши
    -0.74
     wireType
    -0.71
    POSITIVE LOGITS
    @[+][
    0.44
    colgroup
    0.44
     pro
    0.42
    thwaite
    0.41
     s
    0.41
     progress
    0.37
    سو
    0.36
    iertes
    0.36
    ORTH
    0.35
    currentColor
    0.35
    Activations Density 2.600%

    No Known Activations