© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122239
    Prev
    Next
    INDEX
    Explanations

    angle or Rome location

    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_3_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
    at
    0.89
    n
    0.83
    ला
    0.74
    ה
    0.72
    ير
    0.71
    خ
    0.71
    ab
    0.70
    art
    0.70
    ת
    0.68
    ata
    0.67
    POSITIVE LOGITS
    _
    0.77
    ل
    0.64
    л
    0.64
    λία
    0.61
     ilegal
    0.59
     batal
    0.59
     există
    0.59
     Func
    0.57
     Lists
    0.57
    )
    0.57
    Activations Density 0.000%

    No Known Activations