© 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. 8077
    Prev
    Next
    INDEX
    Explanations

    language related to legal documents, patents, or technical manuals.

    oai_token-act-pair · gemini-2.0-flash

    hit or cut

    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
    первых
    -0.54
    EndContext
    -0.44
    ̙
    -0.43
    fromUtf
    -0.42
    setupUi
    -0.42
    '],$
    -0.41
    зможно
    -0.41
    onames
    -0.41
     Pinn
    -0.41
    SPATH
    -0.41
    POSITIVE LOGITS
     hit
    1.79
     cut
    1.64
    hit
    1.42
    cut
    1.39
    Cut
    1.38
     Cut
    1.32
    Hit
    1.27
     put
    1.23
    Put
    1.17
     Hit
    1.17
    Activations Density 17.293%

    No Known Activations