© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161495
    Prev
    Next
    INDEX
    Explanations

    blight or blandford

    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_2_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
     I
    1.38
    ᾧ
    1.14
    Ἠ
    1.09
    قية
    1.02
     reorganization
    1.01
    ెల
    0.99
     Susana
    0.98
     Watford
    0.97
     Lupus
    0.97
    ق
    0.97
    POSITIVE LOGITS
    ent
    1.54
    ec
    1.37
    ani
    1.35
    ek
    1.30
    io
    1.27
    .
    1.27
    you
    1.23
    ре
    1.23
    ра
    1.22
    p
    1.20
    Activations Density 0.000%

    No Known Activations