© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246154
    Prev
    Next
    INDEX
    Explanations

    index variable i

    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_40_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
    anden
    0.41
     ফিরিয়ে
    0.40
    odan
    0.39
    燧
    0.38
    azz
    0.37
    きっかけ
    0.37
    素材
    0.36
     శి
    0.36
    anteen
    0.35
    覚
    0.35
    POSITIVE LOGITS
     Ocean
    0.46
     Loco
    0.44
     loco
    0.42
     Bewer
    0.42
    Succ
    0.41
     Succ
    0.40
     بقت
    0.40
     jigs
    0.40
    ственными
    0.40
    jó
    0.40
    Activations Density 0.001%

    No Known Activations