© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 195930
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    Moves
    0.43
     intending
    0.43
    chell
    0.42
    甛
    0.42
    izion
    0.41
     mueve
    0.41
     industry
    0.40
     กําลัง
    0.40
     intend
    0.39
     intends
    0.39
    POSITIVE LOGITS
     NEC
    0.37
     times
    0.37
    ឱ
    0.36
     মন্দ
    0.36
     wür
    0.34
    читать
    0.34
     τὰ
    0.34
     relentlessly
    0.33
     hip
    0.33
     term
    0.33
    Activations Density 0.002%

    No Known Activations