© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7048
    Prev
    Next
    INDEX
    Explanations

    names which are possibly misspelled, transliterated, or non-English

    oai_token-act-pair · gemini-2.0-flash

    place names

    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
    لكتر
    -0.32
    [++
    -0.29
     precise
    -0.28
     triple
    -0.28
    フォーマンス
    -0.27
     என்ப
    -0.27
     permutations
    -0.27
     respective
    -0.27
     solid
    -0.27
     transparence
    -0.26
    POSITIVE LOGITS
    出版年
    0.36
    MigrationBuilder
    0.35
    osoba
    0.34
    riki
    0.34
    ibra
    0.33
    mær
    0.33
    faro
    0.33
     chré
    0.33
    nione
    0.33
    BASELINE
    0.32
    Activations Density 12.335%

    No Known Activations