© 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. 8433
    Prev
    Next
    INDEX
    Explanations

    HTML tags and related formatting and structural elements

    oai_token-act-pair · gemini-2.0-flash

    HTML heading tags

    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
    "]));
    -0.53
    )}</
    -0.52
    ")));
    -0.52
    createCanvas
    -0.48
    Diweddarwch
    -0.44
    }*/
    -0.42
    </tfoot>
    -0.41
    ]";
    -0.41
    ")]
    -0.41
    "]];
    -0.41
    POSITIVE LOGITS
    ToMany
    0.74
     Dostupné
    0.73
    migrationBuilder
    0.70
    Показать
    0.69
    Revenir
    0.64
     Oncol
    0.64
    PagerAdapter
    0.63
    principalTable
    0.63
     Sleeve
    0.62
     <<<<<<<<<<<<<<
    0.61
    Activations Density 13.351%

    No Known Activations