© 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. 39330
    Prev
    Next
    INDEX
    Explanations

    army, wrestling, groups

    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
    banam
    0.72
    žal
    0.70
    نا
    0.61
     کھول
    0.61
    inį
    0.61
    <0xAE>
    0.60
    villa
    0.60
    ваме
    0.60
    vyšší
    0.60
     मजबूती
    0.59
    POSITIVE LOGITS
    ↵↵
    1.13
    6
    1.00
    ↵↵↵
    0.91
    9
    0.83
    0.83
    5
    0.82
     a
    0.79
    }\
    0.79
    8
    0.76
    </h3>
    0.76
    Activations Density 0.000%

    No Known Activations