© 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. 5665
    Prev
    Next
    INDEX
    Explanations

    the prefix "imp"

    oai_token-act-pair · gemini-2.0-flash

    technical jargon and terms

    np_token-act-pair-logits · gpt-4o-mini

    imp

    np_max-act-logits · gemini-2.0-flash
    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
    ühnen
    -0.43
     Darauf
    -0.43
    XmlEnum
    -0.41
     Moscou
    -0.40
    Performing
    -0.40
    siąż
    -0.40
     segre
    -0.39
    elesaikan
    -0.39
    tvguidetime
    -0.39
     belakang
    -0.39
    POSITIVE LOGITS
     مشين
    0.81
     ReactDOM
    0.69
    RenderAtEndOf
    0.62
    HttpFoundation
    0.61
    LLocation
    0.59
    bParam
    0.58
     мәкал
    0.58
    basicConfig
    0.58
     NSCoder
    0.57
    LabelTagHelper
    0.57
    Activations Density 0.270%

    No Known Activations