© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108334
    Prev
    Next
    INDEX
    Explanations

    Tyler followed by names/titles

    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_1_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
    ى
    1.67
    _
    1.41
    ↵
    1.38
    س
    1.16
    st
    1.08
    ことは
    1.05
    .
    1.05
    ро
    1.04
    f
    1.04
    ש
    1.02
    POSITIVE LOGITS
    is
    1.16
    ۰۰
    0.93
    ﻋ
    0.89
    ER
    0.87
    ética
    0.86
    ální
    0.85
    OV
    0.82
    EUR
    0.82
     niedrig
    0.81
    ००
    0.80
    Activations Density 0.001%

    No Known Activations