© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203065
    Prev
    Next
    INDEX
    Explanations

    introducing or listing

    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_12_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
    成
    0.62
    إ
    0.57
    雷
    0.56
    سون
    0.55
    ﻧ
    0.55
    その
    0.53
    azi
    0.52
    微
    0.51
    ata
    0.50
     resultado
    0.50
    POSITIVE LOGITS
    ancı
    0.64
    ′,
    0.61
    <0x80>
    0.61
    limiting
    0.60
    dated
    0.60
    appropriate
    0.59
    ા
    0.59
    LIMIT
    0.59
    t
    0.57
     restraining
    0.56
    Activations Density 0.005%

    No Known Activations