© 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. 135060
    Prev
    Next
    INDEX
    Explanations

    Telegram and Savior bots/groups

    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
    p
    2.06
    m
    1.78
    t
    1.66
    c
    1.61
    l
    1.59
    ni
    1.53
    ش
    1.53
    ни
    1.38
    v
    1.34
    y
    1.32
    POSITIVE LOGITS
    дцать
    1.06
     važ
    0.98
    ﻓ
    0.96
    జేపీ
    0.94
     wäre
    0.94
    ?
    0.93
     mache
    0.91
     riport
    0.91
     ipotesi
    0.91
     dioxide
    0.91
    Activations Density 0.000%

    No Known Activations