© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194229
    Prev
    Next
    INDEX
    Explanations

    ann, ann-, or city names

    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_4_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
     mairie
    0.97
     danno
    0.93
    ו
    0.86
     chasse
    0.78
     parade
    0.75
    oltre
    0.75
     procession
    0.75
    かと
    0.75
     GPIO
    0.74
     reflet
    0.74
    POSITIVE LOGITS
    ing
    1.33
    t
    1.12
    ת
    1.12
    ü
    1.09
    ة
    1.08
    ال
    1.07
    ри
    1.05
    ين
    1.05
    k
    1.05
    is
    1.05
    Activations Density 0.000%

    No Known Activations