© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28142
    Prev
    Next
    INDEX
    Explanations

    greetings

    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_40_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
     Fertility
    0.43
    geld
    0.40
     heel
    0.38
    odh
    0.37
    anted
    0.36
     환
    0.36
     fertility
    0.36
    nesday
    0.36
    sys
    0.36
    AED
    0.36
    POSITIVE LOGITS
     mirrors
    0.42
     southwestern
    0.42
     зерка
    0.42
     southern
    0.37
     mirrored
    0.37
     mirror
    0.37
     bears
    0.37
    واج
    0.37
    깻
    0.37
    Chad
    0.36
    Activations Density 0.021%

    No Known Activations