© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 85120
    Prev
    Next
    INDEX
    Explanations

    Main

    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_23_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
    郄
    0.46
    UpdateRequest
    0.41
     называют
    0.41
    issie
    0.40
    UNION
    0.39
    ுண்டு
    0.39
    り返
    0.39
    UseCase
    0.38
    稱為
    0.37
    HCl
    0.37
    POSITIVE LOGITS
     _
    0.43
     []
    0.42
     cont
    0.41
     preface
    0.40
     una
    0.40
    literally
    0.39
     Israel
    0.38
    a
    0.38
     ]
    0.38
     m
    0.38
    Activations Density 0.002%

    No Known Activations