© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253655
    Prev
    Next
    INDEX
    Explanations

    diary entry

    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
     N
    0.78
     nib
    0.70
    Nib
    0.64
     Nib
    0.61
    nib
    0.60
     الن
    0.59
    N
    0.57
     BN
    0.57
    BN
    0.57
     NW
    0.56
    POSITIVE LOGITS
     subsum
    0.39
    attempt
    0.38
     duly
    0.38
    ણી
    0.37
     Trojan
    0.37
     препят
    0.36
     fra
    0.36
     ATL
    0.36
    entrance
    0.36
     വി
    0.35
    Activations Density 0.106%

    No Known Activations