© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103636
    Prev
    Next
    INDEX
    Explanations

    Of course

    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_1_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
    I
    1.12
    ot
    1.10
    W
    1.04
    ли
    0.96
    ।
    0.91
    त
    0.89
    il
    0.88
    v
    0.88
    დ
    0.88
     (
    0.86
    POSITIVE LOGITS
    an
    1.10
    이지만
    0.93
     infringing
    0.88
    та
    0.84
     και
    0.83
     incriminating
    0.83
    ຈະ
    0.82
    anın
    0.80
     for
    0.79
    の色
    0.79
    Activations Density 0.001%

    No Known Activations