© 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. 14757
    Prev
    Next
    INDEX
    Explanations

    fragments of URLs and words from Indian languages particularly related to months and festivals.

    oai_token-act-pair · gemini-2.0-flash

    iz

    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
    d
    -0.69
    k
    -0.61
    g
    -0.60
    p
    -0.59
    f
    -0.59
    sp
    -0.59
    c
    -0.56
    KS
    -0.56
    m
    -0.56
    SC
    -0.54
    POSITIVE LOGITS
    AnchorStyles
    0.78
     kasarigan
    0.68
    AddHtmlAttribute
    0.64
    edig
    0.63
    IBOutlet
    0.61
    apimachinery
    0.61
    лтамалар
    0.60
    MigrationBuilder
    0.60
    esez
    0.60
    setObjectName
    0.59
    Activations Density 2.514%

    No Known Activations