© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157842
    Prev
    Next
    INDEX
    Explanations

    schindler's list

    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_2_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
    ться
    1.27
    ある
    1.19
    ний
    1.17
    са
    1.12
    த்தில்
    1.11
    ﺯ
    1.10
    もちろん
    1.08
     услу
    1.07
    ρα
    1.05
    ম্বা
    1.03
    POSITIVE LOGITS
    in
    1.30
     I
    1.26
    ing
    1.07
    í
    1.05
    (
    0.98
     it
    0.96
    h
    0.95
    b
    0.94
    ز
    0.93
    eran
    0.93
    Activations Density 0.000%

    No Known Activations