© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126611
    Prev
    Next
    INDEX
    Explanations

    symmetry and reflection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
     axial
    0.53
     Backward
    0.50
     Axial
    0.49
     Axi
    0.43
     backwards
    0.42
    backward
    0.41
     backward
    0.41
    轴
    0.41
    axial
    0.40
     pusat
    0.40
    POSITIVE LOGITS
    UnifiedTopology
    0.39
    igata
    0.36
    omorph
    0.36
    idina
    0.36
    джа
    0.36
    StateManager
    0.36
    რთ
    0.35
    aines
    0.35
    ilden
    0.35
    威
    0.35
    Activations Density 0.008%

    No Known Activations