© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257714
    Prev
    Next
    INDEX
    Explanations

    past tense verbs indicating completion

    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_22_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
    [
    0.46
    lavery
    0.42
    _.
    0.42
    Angela
    0.41
    Har
    0.41
    angel
    0.40
    amh
    0.40
     last
    0.40
     eleventh
    0.39
    ുകയാണ്
    0.39
    POSITIVE LOGITS
     ambientes
    0.46
    廁
    0.45
     rápido
    0.44
    гем
    0.44
    𝓮
    0.44
    কাঠ
    0.44
     château
    0.44
     músc
    0.44
     comentário
    0.44
    空間
    0.43
    Activations Density 0.000%

    No Known Activations