© 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. 3902
    Prev
    Next
    INDEX
    Explanations

    capitalized or uncapitalized "s" at the beginning of words.

    oai_token-act-pair · gemini-2.0-flash

    s

    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
    IsMutable
    -0.64
     للاسماء
    -0.58
     noDo
    -0.56
    PerformLayout
    -0.55
    ByVersion
    -0.54
    RetentionPolicy
    -0.52
     تكبرها
    -0.52
    bootstrapcdn
    -0.52
    verwijspagina
    -0.50
     beginnetje
    -0.50
    POSITIVE LOGITS
    aints
    0.56
    tableFuture
    0.56
    AutoField
    0.55
    te
    0.55
    TE
    0.52
    avannah
    0.51
    wab
    0.51
    un
    0.51
    kjø
    0.50
    av
    0.50
    Activations Density 2.895%

    No Known Activations