© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43471
    Prev
    Next
    INDEX
    Explanations

    significantly varies

    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_13_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
    -
    0.55
     prevision
    0.55
    ^{-}\
    0.54
    ug
    0.54
     tormented
    0.53
    𝐭
    0.53
     bluish
    0.52
    spiration
    0.52
    ata
    0.51
     پروژه
    0.50
    POSITIVE LOGITS
    ،
    0.76
    ，
    0.72
     ،
    0.71
     italiana
    0.66
     italiano
    0.64
     Chas
    0.64
     Coll
    0.63
     Patterns
    0.63
     Constraints
    0.62
     Beat
    0.60
    Activations Density 0.041%

    No Known Activations