© 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. 28048
    Prev
    Next
    INDEX
    Explanations

    /

    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
     inquest
    0.47
     screw
    0.44
     tonnage
    0.42
     differentiated
    0.41
     differentiation
    0.40
     Egyptian
    0.39
     square
    0.39
    ቸ
    0.39
     tuj
    0.38
     French
    0.38
    POSITIVE LOGITS
     bağlant
    0.44
     зарегистри
    0.38
     kayıt
    0.37
     Fell
    0.37
     Viper
    0.37
     Kole
    0.37
    ubu
    0.36
     Verbindung
    0.36
    viper
    0.36
    👾
    0.36
    Activations Density 0.001%

    No Known Activations