© 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. 45570
    Prev
    Next
    INDEX
    Explanations

    Pavlov's House, Ekman, Forbes

    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
    м
    0.73
    ू
    0.65
    л
    0.64
    ро
    0.63
    ર
    0.62
    ل
    0.60
    لای
    0.58
    ών
    0.57
     rumbo
    0.56
    ல்
    0.55
    POSITIVE LOGITS
    1
    0.79
    on
    0.73
    O
    0.70
    for
    0.68
     for
    0.68
    };
    0.67
    .
    0.66
    ।
    0.65
    Forbes
    0.62
    。
    0.62
    Activations Density 0.007%

    No Known Activations