© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 178240
    Prev
    Next
    INDEX
    Explanations

    speculative or descriptive phrases

    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_29_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
     انسانی
    0.36
     WOULD
    0.35
    することができる
    0.35
     ხელ
    0.34
     INR
    0.33
     청
    0.33
     COULD
    0.33
     право
    0.33
     논
    0.33
     POSSIBLE
    0.33
    POSITIVE LOGITS
     subspecies
    0.39
     schools
    0.36
     dimes
    0.36
    sl
    0.36
     quarterfinals
    0.36
     dime
    0.35
     competitions
    0.35
    Mâ
    0.35
     Martian
    0.34
     quarterbacks
    0.34
    Activations Density 0.058%

    No Known Activations