© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13722
    Prev
    Next
    INDEX
    Explanations

    statements about possibilities

    oai_token-act-pair · gemini-2.0-flash

    possibilities and impossibilities

    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
     availability
    -0.96
     availa
    -0.85
     disponibilité
    -0.83
     disponib
    -0.82
    eable
    -0.80
     Availability
    -0.79
     Available
    -0.78
     available
    -0.77
     impossibility
    -0.77
    hable
    -0.76
    POSITIVE LOGITS
    awtextra
    0.52
     GenerationType
    0.44
    ServletException
    0.43
    AutoresizingMask
    0.42
     NgModule
    0.42
     Penh
    0.41
     pulumi
    0.41
    :][
    0.40
     Réponses
    0.39
    opot
    0.39
    Activations Density 1.599%

    No Known Activations