© 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. 58789
    Prev
    Next
    INDEX
    Explanations

    anger management

    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
    ли
    0.70
    (
    0.59
    㑹
    0.58
     Алексе
    0.57
    이다
    0.56
    ig
    0.55
     científicos
    0.55
    лни
    0.54
    un
    0.53
     Peña
    0.52
    POSITIVE LOGITS
    ای
    0.67
    u
    0.66
    কে
    0.65
    вых
    0.65
    ール
    0.63
     to
    0.61
    st
    0.60
    数据
    0.59
    dı
    0.59
    dh
    0.58
    Activations Density 0.000%

    No Known Activations