© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193714
    Prev
    Next
    INDEX
    Explanations

    floored it

    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_27_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
     হেঁ
    0.43
    imerk
    0.41
     വാർത്ത
    0.38
    φή
    0.37
    徒歩
    0.37
     পায়ে
    0.37
    氳
    0.37
    เดิน
    0.37
    redund
    0.36
    acetyl
    0.36
    POSITIVE LOGITS
     PROGRAM
    0.36
     Program
    0.35
     An
    0.34
    ರಣ
    0.33
    ]</
    0.33
     Meat
    0.33
    からない
    0.33
    되었다
    0.33
    грамма
    0.33
     Land
    0.33
    Activations Density 0.005%

    No Known Activations