© 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. 53567
    Prev
    Next
    INDEX
    Explanations

    can do things

    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
    Stre
    0.42
    do
    0.39
     પાસેથી
    0.39
    =$_
    0.38
    Text
    0.37
    Assessment
    0.37
     Downs
    0.37
    गार
    0.37
     Lifting
    0.36
    দা
    0.36
    POSITIVE LOGITS
     circumstance
    0.42
     Mikolai
    0.39
    ilus
    0.39
     eloqu
    0.38
     Sabbath
    0.38
    恆
    0.38
    uron
    0.37
     shouldUse
    0.37
     UU
    0.36
     Jolla
    0.36
    Activations Density 0.003%

    No Known Activations