© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30273
    Prev
    Next
    INDEX
    Explanations

    deepfakes

    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_7_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
     a
    1.34
     is
    1.22
     conno
    1.08
     with
    1.00
     talisman
    0.99
     stallion
    0.98
     semicircle
    0.98
     goddess
    0.97
     gamer
    0.97
     (
    0.96
    POSITIVE LOGITS
    é
    1.29
    在
    1.24
    of
    1.23
    in
    1.19
    us
    1.16
    ك
    1.10
    the
    1.09
    ál
    1.08
    og
    1.06
    ن
    1.04
    Activations Density 0.001%

    No Known Activations