© 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. 4199
    Prev
    Next
    INDEX
    Explanations

    adjectives and descriptive terms.

    oai_token-act-pair · gemini-2.0-flash

    societal impacts

    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
     مرئيه
    -0.72
     apparent
    -0.70
    MigrationBuilder
    -0.57
    脚注の使い方
    -0.57
     evident
    -0.56
     otomatig
    -0.56
     observed
    -0.54
     seemingly
    -0.54
    AddTagHelper
    -0.54
     measured
    -0.53
    POSITIVE LOGITS
    ImageContext
    0.56
     particulières
    0.54
    ükemmel
    0.52
     engraçadas
    0.49
     spéciaux
    0.49
     vermelhas
    0.49
     complètes
    0.48
    trois
    0.48
     charité
    0.48
     Normdatei
    0.47
    Activations Density 7.649%

    No Known Activations