© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49282
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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_55_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
     X
    0.95
     XX
    0.94
     nn
    0.83
    XX
    0.82
     xx
    0.81
     xxx
    0.81
     NN
    0.79
     n
    0.78
    XXXX
    0.76
     XXX
    0.76
    POSITIVE LOGITS
    ֣
    0.37
    టికి
    0.35
    Fo
    0.35
    My
    0.35
    swell
    0.35
     MAGAZINE
    0.34
    想不到
    0.34
    edom
    0.34
    Rodr
    0.34
     My
    0.33
    Activations Density 0.061%

    No Known Activations