© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215553
    Prev
    Next
    INDEX
    Explanations

    how to

    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_31_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
    assembl
    0.41
     cæ
    0.38
    --“
    0.37
     dry
    0.34
     assembl
    0.34
     के
    0.33
    ång
    0.33
     dudes
    0.33
     prejudiced
    0.33
     pang
    0.32
    POSITIVE LOGITS
     முதுகு
    0.45
     가지
    0.43
    𝗶
    0.41
     चौथ
    0.40
     возможность
    0.40
    椷
    0.40
     possibilidade
    0.38
     దాని
    0.38
     Sith
    0.37
    須
    0.37
    Activations Density 0.009%

    No Known Activations