© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 141790
    Prev
    Next
    INDEX
    Explanations

    masturbation or mast cells

    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_0_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
    та
    1.88
    ور
    1.88
    ut
    1.77
    ون
    1.68
    Q
    1.63
    AL
    1.62
    AR
    1.60
    IC
    1.60
    lara
    1.60
    K
    1.59
    POSITIVE LOGITS
    o
    1.30
    s
    1.16
    a
    1.08
    ς
    1.06
    నూ
    1.01
    し
    1.01
     immobil
    0.99
     decentral
    0.99
     ссы
    0.99
    í
    0.98
    Activations Density 0.000%

    No Known Activations