© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154121
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_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
    ↵
    0.47
    but
    0.46
    ent
    0.46
    ney
    0.45
    a
    0.44
    ↵↵
    0.44
    riven
    0.43
    bank
    0.43
    N
    0.43
    5
    0.43
    POSITIVE LOGITS
     erinnert
    0.55
     عدد
    0.51
     போல
    0.51
     tanggal
    0.50
     hatten
    0.50
    عدد
    0.50
     oggetto
    0.50
    ಿಕೆ
    0.49
     invariable
    0.49
     ตอน
    0.49
    Activations Density 0.000%

    No Known Activations