© 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. 5534
    Prev
    Next
    INDEX
    Explanations

    code snippets from different languages

    oai_token-act-pair · gemini-2.0-flash

    various prefixes and suffixes of words

    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
    τός
    -0.71
     himſelf
    -0.69
     Reſ
    -0.68
     يتيمه
    -0.68
     Jefus
    -0.67
     Efq
    -0.67
    ſelf
    -0.66
    DeleteBehavior
    -0.65
    spesies
    -0.63
    MigrationBuilder
    -0.63
    POSITIVE LOGITS
     Moo
    0.45
    ITAGE
    0.44
    ющего
    0.44
    Soorten
    0.43
    Искәрмәләр
    0.43
    AnchorStyles
    0.41
    msgTypes
    0.40
    nologue
    0.40
    sego
    0.40
    TintMode
    0.40
    Activations Density 0.294%

    No Known Activations