© 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. 7810
    Prev
    Next
    INDEX
    Explanations

    DNA sequences and romanizations

    oai_token-act-pair · 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
     WL
    -0.70
     MW
    -0.67
     BV
    -0.63
     wl
    -0.62
     PW
    -0.62
     HU
    -0.61
     RW
    -0.60
     WB
    -0.59
     w
    -0.59
    HU
    -0.58
    POSITIVE LOGITS
     ModelExpression
    0.65
    IntoConstraints
    0.49
    CreateIndex
    0.43
    itzenden
    0.43
     chofe
    0.43
    Cristo
    0.42
     Савезне
    0.42
     kit
    0.42
     CURIAM
    0.42
     Cientí
    0.42
    Activations Density 1.512%

    No Known Activations