© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154350
    Prev
    Next
    INDEX
    Explanations

    torture

    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_23_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
    īt
    0.42
     nabíd
    0.42
    jillo
    0.40
    edish
    0.38
    ý
    0.36
    ività
    0.36
    ajos
    0.36
    ído
    0.36
     кур
    0.35
    ஞ்சம்
    0.34
    POSITIVE LOGITS
     ज्वाला
    0.41
    urne
    0.41
     pila
    0.39
     वहां
    0.38
    Barn
    0.38
    ुली
    0.38
     लाहि
    0.37
    pheromone
    0.37
    冤
    0.37
     Grecia
    0.37
    Activations Density 0.001%

    No Known Activations