© 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. 1376
    Prev
    Next
    INDEX
    Explanations

    superscripted numbers enclosed in dollar signs

    oai_token-act-pair · gemini-2.0-flash

    mathematical/code symbols

    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
     تكبرها
    -0.59
     Instinct
    -0.53
    soup
    -0.52
     Feeds
    -0.52
    CESO
    -0.52
     tartalomajánló
    -0.49
     Dernière
    -0.48
     Waar
    -0.47
     seguirá
    -0.47
     Unders
    -0.47
    POSITIVE LOGITS
    sqcup
    0.69
    WebElementEntity
    0.67
    varrho
    0.65
    Bigr
    0.61
    fbox
    0.60
    ServletConfig
    0.60
    ddagger
    0.58
    URLException
    0.58
    urlencoded
    0.56
    ]--;
    0.55
    Activations Density 2.529%

    No Known Activations