© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142224
    Prev
    Next
    INDEX
    Explanations

    defining or redefining concepts

    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
    in
    1.93
    م
    1.79
    an
    1.70
    i
    1.66
    ur
    1.46
    ే
    1.45
    it
    1.44
    ان
    1.41
    த்தில்
    1.41
    ก็
    1.41
    POSITIVE LOGITS
    dır
    1.24
    TorpedoStore
    1.24
    ﻧ
    1.21
    ﺑ
    1.20
    ﮔ
    1.20
    '
    1.19
    ﻫ
    1.19
    دى
    1.18
    "/"
    1.17
    지만
    1.16
    Activations Density 0.001%

    No Known Activations