© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30511
    Prev
    Next
    INDEX
    Explanations

    aggregate, particleboard

    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_7_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
    ↵↵
    0.28
     detour
    0.23
     rumble
    0.23
    ナ
    0.22
    p
    0.22
     तौर
    0.22
     لے
    0.21
     plunge
    0.21
     sním
    0.20
     participle
    0.20
    POSITIVE LOGITS
    ي
    0.33
    el
    0.33
    ی
    0.31
     are
    0.30
    ag
    0.29
    ai
    0.29
     an
    0.28
     arbeitet
    0.27
    ки
    0.27
     welche
    0.27
    Activations Density 0.001%

    No Known Activations