© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 33952
    Prev
    Next
    INDEX
    Explanations

    Mohenjo-daro, Harappa

    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
    es
    1.66
    im
    1.54
    s
    1.54
    ik
    1.51
    7
    1.51
    z
    1.45
    se
    1.44
    ak
    1.43
    ti
    1.41
    v
    1.40
    POSITIVE LOGITS
     be
    1.16
     to
    1.15
    で
    1.14
    に
    1.06
    ྒྱ
    1.05
    から
    1.04
    と
    1.04
    ﻟ
    1.04
    ۰
    1.02
    ными
    0.98
    Activations Density 0.000%

    No Known Activations