© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37866
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    ре
    0.71
    1
    0.71
    л
    0.67
     postage
    0.64
    н
    0.64
    ↵
    0.63
     can
    0.63
    ר
    0.56
    3
    0.55
    ườ
    0.54
    POSITIVE LOGITS
    াইয়৷
    0.73
    tries
    0.67
    rikan
    0.59
    in
    0.58
    pots
    0.58
    izantes
    0.58
     دیکھ
    0.57
    uins
    0.57
    tura
    0.57
     खिलाफ
    0.57
    Activations Density 0.000%

    No Known Activations