© 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. 1074
    Prev
    Next
    INDEX
    Explanations

    the letter "H" followed by a period or digit

    oai_token-act-pair · gemini-2.0-flash

    H

    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
     ویکی‌پدیا
    -0.75
    EndGlobalSection
    -0.63
     ويكيميديا
    -0.61
    脚注の使い方
    -0.60
    lês
    -0.58
     actionMode
    -0.56
    <bos>
    -0.56
    Vidite
    -0.56
     yyr
    -0.56
    OGND
    -0.55
    POSITIVE LOGITS
     noch
    0.48
    URLException
    0.45
    ammen
    0.45
    dien
    0.43
    Encoding
    0.43
    icken
    0.42
    portlet
    0.42
    ようになりました
    0.42
    imel
    0.42
     lenker
    0.41
    Activations Density 2.141%

    No Known Activations