© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 31514
    Prev
    Next
    INDEX
    Explanations

    improvise / improvised

    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_7_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
    8
    1.29
    ↵
    1.27
    in
    1.26
    6
    1.23
    3
    1.17
    4
    1.16
    .
    1.14
    9
    1.14
    2
    1.13
    1
    1.09
    POSITIVE LOGITS
    ک
    1.11
     and
    1.05
    𝒈
    0.97
     अच्छी
    0.96
    抂
    0.92
     to
    0.89
     estudios
    0.86
     แต
    0.86
     distinguishers
    0.84
    すでに
    0.84
    Activations Density 0.003%

    No Known Activations