© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80815
    Prev
    Next
    INDEX
    Explanations

    superstitions, super, súper

    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_0_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
    _
    1.43
    a
    1.41
    。
    1.39
    া
    1.29
    ा
    1.20
    ли
    1.17
    ́c
    1.16
    ۱
    1.16
    ه
    1.15
     aaya
    1.13
    POSITIVE LOGITS
    ل
    1.96
    ल
    1.74
    im
    1.59
    m
    1.56
     is
    1.50
    ל
    1.48
    u
    1.41
    w
    1.39
    म
    1.39
    র
    1.38
    Activations Density 0.000%

    No Known Activations