© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231901
    Prev
    Next
    INDEX
    Explanations

    molars

    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_6_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
    HE
    1.15
    HER
    1.13
    ro
    1.12
    O
    1.10
    AL
    1.09
    TE
    1.09
    IM
    1.07
    Ш
    1.06
    i
    1.05
    l
    1.05
    POSITIVE LOGITS
    ่
    1.00
     lai
    0.92
    ').
    0.80
    ма
    0.78
    <0x80>
    0.76
    おそらく
    0.75
     squiggle
    0.75
    poetrylovers
    0.75
     Aniston
    0.75
    ).
    0.74
    Activations Density 0.000%

    No Known Activations