© 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. 75237
    Prev
    Next
    INDEX
    Explanations

    word count estimates

    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
    aded
    0.26
    驒
    0.26
    рах
    0.26
     Srps
    0.26
    ayı
    0.24
    ovao
    0.24
     成
    0.23
     request
    0.23
     ዘ
    0.23
     enjoin
    0.23
    POSITIVE LOGITS
    ☞
    0.28
     सेट
    0.28
     अका
    0.27
    ორე
    0.27
    セット
    0.25
    버
    0.25
    À
    0.25
    尬
    0.25
     سلا
    0.25
    ülle
    0.25
    Activations Density 0.001%

    No Known Activations