© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201403
    Prev
    Next
    INDEX
    Explanations

    mov

    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_46_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
    rescence
    0.39
    œuf
    0.39
    Saint
    0.36
    iconductor
    0.36
    opez
    0.36
     непло
    0.35
    羊
    0.35
    Ꮣ
    0.35
     Amendment
    0.35
    щення
    0.34
    POSITIVE LOGITS
     кине
    0.46
     kinematics
    0.45
    heuristic
    0.43
     gait
    0.42
     Garr
    0.42
     goTo
    0.40
     Gone
    0.40
     derby
    0.40
     Federico
    0.40
     kinemat
    0.39
    Activations Density 0.000%

    No Known Activations