© 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. 83686
    Prev
    Next
    INDEX
    Explanations

    puppets

    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
    ing
    1.81
     de
    1.74
    e
    1.55
     que
    1.53
    の
    1.51
     can
    1.42
     that
    1.39
    ة
    1.38
    ’
    1.36
     la
    1.30
    POSITIVE LOGITS
    N
    1.40
     accentuated
    1.28
    clusive
    1.14
    ालय
    1.13
    ﻥ
    1.13
    lng
    1.12
    W
    1.09
     prepd
    1.05
    σμ
    1.05
    ਨ
    1.05
    Activations Density 0.000%

    No Known Activations