© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133014
    Prev
    Next
    INDEX
    Explanations

    kmt, kgs, kashi, kanten, knust

    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
    트
    1.72
    는
    1.56
    다음
    1.50
    사
    1.45
    न
    1.43
    다
    1.41
    च
    1.38
    ש
    1.38
    자
    1.36
    ی
    1.35
    POSITIVE LOGITS
    om
    1.63
    are
    1.61
    1.61
    .
    1.40
    of
    1.36
    on
    1.30
    ist
    1.30
    am
    1.27
     for
    1.26
    ay
    1.18
    Activations Density 0.000%

    No Known Activations