© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112912
    Prev
    Next
    INDEX
    Explanations

    judgments

    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_2_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
    a
    1.52
    of
    1.34
    p
    1.27
    f
    1.23
    ن
    1.13
    an
    1.13
    ty
    1.12
    that
    1.11
    ung
    1.10
    ні
    1.05
    POSITIVE LOGITS
    ции
    1.32
     in
    1.23
    મ
    1.12
     deducted
    1.09
    ту
    1.09
    ння
    1.06
    સ
    1.06
     as
    1.05
    ی
    1.05
    დ
    1.05
    Activations Density 0.001%

    No Known Activations