© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 167918
    Prev
    Next
    INDEX
    Explanations

    say "code symbols"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defe
    0.39
     ограничен
    0.37
    );"
    0.36
     pretends
    0.36
    ()];
    0.35
    %);
    0.34
    ལ
    0.34
    ライド
    0.33
    ());
    0.33
    )$;
    0.33
    POSITIVE LOGITS
    elseif
    0.45
    echo
    0.43
     echo
    0.41
    ]='
    0.41
    independence
    0.38
     .=
    0.38
    })=
    0.38
    ]]=
    0.38
    Conflicts
    0.38
    ancellation
    0.37
    Activations Density 0.000%

    No Known Activations