© 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. 42110
    Prev
    Next
    INDEX
    Explanations

    Object Model

    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
    in
    0.84
    inę
    0.70
    inhas
    0.69
    inama
    0.68
    isjon
    0.61
     شہریوں
    0.59
    ו
    0.59
     molest
    0.59
     financieros
    0.58
    inizi
    0.57
    POSITIVE LOGITS
    :
    0.65
    TING
    0.64
    го
    0.60
    oh
    0.59
    ;
    0.58
    ៧
    0.57
    ft
    0.54
     صعبه
    0.54
    ght
    0.53
    、
    0.53
    Activations Density 0.003%

    No Known Activations