© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18796
    Prev
    Next
    INDEX
    Explanations

    loose typing, coupling, brush strokes

    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_15_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
     skipped
    0.63
     n
    0.59
    逆
    0.57
    רו
    0.51
     Jansen
    0.50
    цер
    0.49
    }^{*}$,
    0.49
    Make
    0.47
     chamado
    0.47
    зел
    0.47
    POSITIVE LOGITS
    už
    0.55
    㷅
    0.53
     ใน
    0.52
     오랜
    0.51
     :(
    0.50
     نیز
    0.49
     Dacă
    0.48
     În
    0.48
     అతని
    0.48
     များ
    0.48
    Activations Density 0.000%

    No Known Activations