© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97869
    Prev
    Next
    INDEX
    Explanations

    Hello Kitty or scp transfer

    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_14_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
    Els
    0.55
     Recht
    0.54
    Е
    0.52
     강화
    0.50
    VEY
    0.50
    ЕД
    0.49
    ➤
    0.47
     Exploration
    0.46
    Tint
    0.45
     экономического
    0.45
    POSITIVE LOGITS
    ือ
    0.55
    secure
    0.53
     p
    0.52
    icum
    0.52
    ri
    0.52
     or
    0.52
     miserably
    0.52
    しさ
    0.51
    h
    0.51
    re
    0.51
    Activations Density 0.001%

    No Known Activations