© 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. 6426
    Prev
    Next
    INDEX
    Explanations

    text that discusses race and/or racism.

    oai_token-act-pair · gemini-2.0-flash

    Colors

    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
     black
    -1.84
     blue
    -1.84
     red
    -1.70
     brown
    -1.66
    black
    -1.65
    blue
    -1.61
     white
    -1.60
     gray
    -1.59
     grey
    -1.58
     green
    -1.57
    POSITIVE LOGITS
    ISupport
    0.52
    TypeDef
    0.49
    })()
    0.47
     aanges
    0.45
    期刊论文
    0.45
    )"),
    0.44
    UrlResolution
    0.44
    validates
    0.44
    ficamente
    0.43
    subpackage
    0.43
    Activations Density 8.701%

    No Known Activations