© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53323
    Prev
    Next
    INDEX
    Explanations

    preferred vendor

    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_31_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
    क्शन
    0.40
    úr
    0.40
    desired
    0.39
     செயற்க
    0.39
    Wr
    0.38
    engaruhi
    0.38
    ẏ
    0.37
    ους
    0.37
    ErrorHandler
    0.37
     گاه
    0.37
    POSITIVE LOGITS
     circulate
    0.40
    是不是
    0.38
    炰
    0.38
     proofs
    0.38
     NUM
    0.37
     Ache
    0.37
     benchmarks
    0.37
     fend
    0.36
     proof
    0.36
     num
    0.35
    Activations Density 0.089%

    No Known Activations