© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 235868
    Prev
    Next
    INDEX
    Explanations

    directional opposites

    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_25_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
     সাথ
    0.40
     Sanderson
    0.39
     TREAT
    0.39
     blod
    0.38
    র
    0.38
     Winds
    0.38
     departments
    0.37
    干扰
    0.37
     Desktop
    0.37
    astas
    0.37
    POSITIVE LOGITS
     किफ
    0.40
     özellikle
    0.38
    Anyone
    0.38
    𝟭
    0.38
    ならでは
    0.37
    木
    0.37
    Continue
    0.37
     muffled
    0.37
    いただきました
    0.37
    partite
    0.37
    Activations Density 0.001%

    No Known Activations