© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231466
    Prev
    Next
    INDEX
    Explanations

    meditation or measurable

    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_6_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
    y
    1.26
    i
    1.16
    مون
    1.09
    u
    1.09
     filet
    0.95
    ens
    0.86
     sumo
    0.85
    as
    0.84
    l
    0.84
     cooldown
    0.82
    POSITIVE LOGITS
    0
    1.28
    א
    1.16
    _
    1.13
    はじ
    1.05
    ك
    1.04
    K
    1.02
    ನ
    1.00
    на
    0.99
    ל
    0.99
    น
    0.98
    Activations Density 0.000%

    No Known Activations