© 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. 64737
    Prev
    Next
    INDEX
    Explanations

    PHP

    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
    ception
    0.41
     evaluation
    0.39
     Pong
    0.39
    pong
    0.39
     ph
    0.37
     pong
    0.37
     relatives
    0.37
    ઘ
    0.36
     Bonjour
    0.36
     Rage
    0.36
    POSITIVE LOGITS
    ળો
    0.49
    辻
    0.42
     Generating
    0.38
    Generated
    0.38
     Generated
    0.38
     IMMEDI
    0.37
    ddots
    0.36
    벌
    0.36
    IMPORTED
    0.36
    ળા
    0.36
    Activations Density 0.001%

    No Known Activations