© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17903
    Prev
    Next
    INDEX
    Explanations

    code structure definitions

    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_34_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
    踏
    0.40
    platin
    0.38
     richtig
    0.37
     যেটা
    0.37
     এটা
    0.36
     दैट
    0.35
    こんばんは
    0.35
     persisting
    0.35
    гото
    0.34
     чему
    0.34
    POSITIVE LOGITS
    ēm
    0.41
    сову
    0.40
    褻
    0.40
     ώ
    0.37
     tabi
    0.37
     waiver
    0.36
     waive
    0.35
    rocchia
    0.35
     amplitude
    0.35
     Nasr
    0.35
    Activations Density 0.085%

    No Known Activations