© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200080
    Prev
    Next
    INDEX
    Explanations

    marm, Sky, Mountain, star, mammoth, Broadway

    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_12_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
    ggio
    0.64
    tta
    0.55
     Himachal
    0.53
    ಿಸುತ್ತದೆ
    0.52
    assets
    0.50
     weddings
    0.50
     villas
    0.50
     r
    0.49
     flooding
    0.49
     Nepal
    0.49
    POSITIVE LOGITS
     adres
    0.62
     。
    0.54
     directe
    0.54
    㐸
    0.54
     ок
    0.52
     пришли
    0.52
     réponse
    0.51
    ตอบ
    0.51
     обознача
    0.51
     boire
    0.50
    Activations Density 0.000%

    No Known Activations