© 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. 236035
    Prev
    Next
    INDEX
    Explanations

    rocket

    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
     бата
    0.44
    Battery
    0.43
     bateria
    0.42
     Batterie
    0.39
    閨
    0.38
     battery
    0.37
    電池
    0.37
     Battery
    0.36
    蠹
    0.36
     giveaway
    0.36
    POSITIVE LOGITS
    과학
    0.44
     Scientist
    0.44
     과학
    0.43
     scientist
    0.43
    checkable
    0.42
     Curtis
    0.37
    科学
    0.37
     Independ
    0.37
     Aver
    0.37
     இயக்கு
    0.37
    Activations Density 0.000%

    No Known Activations