© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246272
    Prev
    Next
    INDEX
    Explanations

    signs or speech

    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_40_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
     kern
    0.38
    Ń
    0.37
    Song
    0.36
    Elle
    0.36
    र्मु
    0.36
     Kimberly
    0.36
    Kim
    0.35
    ĩ
    0.35
     ÷
    0.35
    낌
    0.35
    POSITIVE LOGITS
     saying
    1.59
     Saying
    1.30
     says
    1.23
    說
    1.20
     dizendo
    1.14
    say
    1.12
    说
    1.12
    says
    1.11
     say
    1.10
     berkata
    1.09
    Activations Density 0.073%

    No Known Activations