© 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. 54394
    Prev
    Next
    INDEX
    Explanations

    Be

    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
     Be
    0.43
    čke
    0.43
    be
    0.42
    Be
    0.41
    anyone
    0.40
    )}}{\
    0.39
     hooked
    0.39
     anyone
    0.38
    zai
    0.38
     wield
    0.37
    POSITIVE LOGITS
     Apar
    0.39
    Simpl
    0.39
     нас
    0.38
     제도
    0.38
    appar
    0.38
    écies
    0.38
    UserProg
    0.38
    
    0.38
    quests
    0.38
     debuts
    0.37
    Activations Density 0.004%

    No Known Activations