© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168348
    Prev
    Next
    INDEX
    Explanations

    return

    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_56_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
    ̭
    0.36
    քում
    0.36
    咟
    0.36
     }>;
    0.35
     Ren
    0.35
    ụp
    0.34
    Ren
    0.34
    䣰
    0.34
     }}{\
    0.33
     Rxb
    0.33
    POSITIVE LOGITS
     returning
    1.70
     возвра
    1.63
     returned
    1.60
     Returning
    1.57
     верну
    1.48
    Returning
    1.48
     return
    1.46
    returning
    1.45
    Returned
    1.41
     returns
    1.39
    Activations Density 0.006%

    No Known Activations