© 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. 18201
    Prev
    Next
    INDEX
    Explanations

    D.C

    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
     consolidated
    0.41
     पाएं
    0.40
    📋
    0.38
    ಶ್ಯ
    0.38
     Moh
    0.37
     качественно
    0.37
     moh
    0.37
     Ramp
    0.37
     auctioned
    0.36
     consolidate
    0.36
    POSITIVE LOGITS
    obedience
    0.41
    णावर
    0.39
     CODE
    0.39
    ácio
    0.38
     surat
    0.38
    heti
    0.37
    deload
    0.37
    ೋ
    0.37
     haud
    0.36
    getCode
    0.36
    Activations Density 0.012%

    No Known Activations