© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111728
    Prev
    Next
    INDEX
    Explanations

    dispute resolution

    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_2_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
    ни
    1.34
    kowe
    1.20
    ون
    1.17
     ও
    1.11
    langan
    1.11
    '
    1.11
    larda
    1.08
    isyon
    1.08
    ির
    1.07
    ל
    1.04
    POSITIVE LOGITS
    .
    1.56
    1
    1.25
    8
    1.20
     as
    1.15
    家
    1.13
    ة
    1.08
    مل
    1.06
    5
    1.05
    4
    1.05
    9
    1.05
    Activations Density 0.001%

    No Known Activations