© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 66727
    Prev
    Next
    INDEX
    Explanations

    strict

    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
     Cambrian
    0.40
     සම්
    0.37
    standards
    0.37
    ![](
    0.37
     standards
    0.37
     strict
    0.36
    uyi
    0.36
    箜
    0.36
     정확
    0.36
     Perspective
    0.35
    POSITIVE LOGITS
     अपराध
    0.49
     crimes
    0.49
     delitos
    0.48
     преступ
    0.47
     crime
    0.46
     infring
    0.43
    犯罪
    0.42
     infraction
    0.41
    crime
    0.41
     criminality
    0.40
    Activations Density 0.000%

    No Known Activations