© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175031
    Prev
    Next
    INDEX
    Explanations

    New York

    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_24_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
    РО
    0.52
    ures
    0.43
    гід
    0.43
    asă
    0.42
     тво
    0.42
    ב
    0.41
    branes
    0.41
    v
    0.40
    wem
    0.40
    ન્મ
    0.39
    POSITIVE LOGITS
     sinister
    0.49
     metamorph
    0.49
     trail
    0.47
     mulberry
    0.47
     singular
    0.46
     limiti
    0.46
     debat
    0.46
     bbox
    0.46
     בי
    0.46
     espalda
    0.46
    Activations Density 0.000%

    No Known Activations