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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42055
    Prev
    Next
    INDEX
    Explanations

    thumbs up/down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    n
    0.79
     verdi
    0.79
    x
    0.78
    b
    0.76
    ي
    0.75
     académ
    0.75
    i
    0.73
     unha
    0.72
     médica
    0.71
    adă
    0.71
    POSITIVE LOGITS
    </h2>
    0.82
    </h3>
    0.77
    िंग
    0.74
    <0x0D>
    0.71
     Risks
    0.71
     pita
    0.68
     Outcomes
    0.68
    र
    0.68
    ियों
    0.67
    ів
    0.67
    Activations Density 0.000%

    No Known Activations