© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131808
    Prev
    Next
    INDEX
    Explanations

    content filters

    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_6_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
    :
    1.00
    ING
    0.99
    /
    0.80
    ):
    0.80
    ة
    0.80
    nagar
    0.79
    h
    0.79
    yte
    0.78
    }:
    0.78
     fifties
    0.77
    POSITIVE LOGITS
    ０
    1.02
    ות
    0.97
    お
    0.91
    ために
    0.89
     rů
    0.88
     Обра
    0.87
    ۰
    0.87
    és
    0.86
     Aquí
    0.86
     drugi
    0.85
    Activations Density 0.006%

    No Known Activations