© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6309
    Prev
    Next
    INDEX
    Explanations

    terms or names associated with ancient Chinese history/mythology

    oai_token-act-pair · gemini-2.0-flash

    words related to actions or movements

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Życiorys
    -0.69
     RouterModule
    -0.66
     '\\;'
    -0.57
    논
    -0.55
    PhysRevD
    -0.54
     which
    -0.54
    onedDateTime
    -0.52
    gypte
    -0.52
     ktor
    -0.51
    which
    -0.51
    POSITIVE LOGITS
     समीक्षाओं
    0.59
     knew
    0.53
    StructEnd
    0.52
     Behind
    0.50
     kicked
    0.49
     took
    0.48
     stepped
    0.48
     Roskov
    0.48
     wrote
    0.47
    GraphicsUnit
    0.47
    Activations Density 1.039%

    No Known Activations