© 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. 127239
    Prev
    Next
    INDEX
    Explanations

    smaller scale

    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
    .
    0.79
    กัน
    0.76
     recibir
    0.73
    、
    0.70
     independente
    0.69
    する
    0.68
    ிகள்
    0.68
    ра
    0.66
     viene
    0.65
    с
    0.64
    POSITIVE LOGITS
    a
    0.97
    ፩
    0.76
    Warum
    0.71
    nash
    0.71
    diaz
    0.71
    nk
    0.70
    aabb
    0.69
    aue
    0.69
    i
    0.69
    gge
    0.67
    Activations Density 0.001%

    No Known Activations