© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197374
    Prev
    Next
    INDEX
    Explanations

    star-struck, awestruck

    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_4_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
    ing
    1.17
    ল
    1.16
    িন
    1.07
    ار
    1.06
    hf
    1.05
    ত
    1.02
    taker
    0.98
    hq
    0.98
    hg
    0.98
    tor
    0.97
    POSITIVE LOGITS
    ف
    1.09
    iv
    0.91
    지
    0.91
    og
    0.89
    m
    0.88
    /
    0.88
    3
    0.87
    ue
    0.82
    最早
    0.80
    mär
    0.79
    Activations Density 0.005%

    No Known Activations