© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220304
    Prev
    Next
    INDEX
    Explanations

    URLs and lists

    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_31_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
     provoquer
    0.13
     injurious
    0.12
     jeunesse
    0.12
    👛
    0.11
     kaisi
    0.11
     amide
    0.11
     erythrocytes
    0.11
    ہد
    0.11
     enzym
    0.11
     fichiers
    0.11
    POSITIVE LOGITS
    e
    0.11
     surprisingly
    0.11
    kel
    0.11
     No
    0.10
     On
    0.10
     Surprisingly
    0.10
    surprisingly
    0.10
     GM
    0.10
    al
    0.10
     P
    0.10
    Activations Density 0.000%

    No Known Activations