© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170380
    Prev
    Next
    INDEX
    Explanations

    Harry Potter / The Hobbit

    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_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    j
    0.32
    7
    0.28
    Var
    0.28
    no
    0.28
    Figs
    0.27
    on
    0.27
    ad
    0.27
    Bolt
    0.27
    Delete
    0.27
    GT
    0.26
    POSITIVE LOGITS
    ailangan
    0.32
     appris
    0.31
     émotion
    0.29
     хочу
    0.28
    缈
    0.28
    祹
    0.28
    更大的
    0.27
    ంచెం
    0.27
     quais
    0.27
     একটা
    0.27
    Activations Density 0.000%

    No Known Activations