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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12248
    Prev
    Next
    INDEX
    Explanations

    the verb "speak" or its variations.

    oai_token-act-pair · gemini-2.0-flash

    speak

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    bootstrapcdn
    -0.86
     &___
    -0.76
     nakalista
    -0.63
    RenderAtEndOf
    -0.63
    enterOuterAlt
    -0.61
     NKC
    -0.59
    Obrázky
    -0.59
    WriteLiteral
    -0.59
    kmäler
    -0.58
    __*/
    -0.57
    POSITIVE LOGITS
    nert
    0.43
     hyperbolic
    0.41
    Conversations
    0.41
     turismo
    0.40
    <!--[
    0.40
     voces
    0.40
     conversational
    0.39
     Toujours
    0.39
     arrivent
    0.39
    Thin
    0.39
    Activations Density 1.354%

    No Known Activations