© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105945
    Prev
    Next
    INDEX
    Explanations

    HR, IHRM, ICL

    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
    to
    1.91
    g
    1.70
    an
    1.57
    c
    1.50
    p
    1.48
    f
    1.44
    t
    1.43
    man
    1.37
    the
    1.34
    z
    1.33
    POSITIVE LOGITS
    (
    1.33
    იდ
    1.27
    ोबर
    1.21
    ۹
    1.19
    I
    1.16
    ۸
    1.16
    ি
    1.12
    ৫
    1.12
    ۵
    1.10
    ни
    1.09
    Activations Density 0.000%

    No Known Activations