© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6094
    Prev
    Next
    INDEX
    Explanations

    words and phrases that frequently occur in scientific or technical documents, like measurement terms, location terms, and references.

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
     to
    -1.18
     for
    -1.09
     with
    -1.03
     from
    -0.98
    ']").
    -0.92
    ).}
    -0.85
    ."),
    -0.85
    ")(
    -0.84
    '>";
    -0.84
    )];
    
    -0.84
    POSITIVE LOGITS
     kvinder
    0.48
     religione
    0.46
     grecque
    0.46
     blitt
    0.45
     nuages
    0.44
     vanske
    0.43
     blevet
    0.43
     sabbia
    0.42
     maux
    0.41
     curieux
    0.41
    Activations Density 31.681%

    No Known Activations