© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23878
    Prev
    Next
    INDEX
    Explanations

    Indic script sounds

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    দের
    0.61
    दी
    0.52
    দে
    0.47
    दा
    0.46
    દી
    0.46
    ദ
    0.45
    ദി
    0.45
    राबाद
    0.42
    ద
    0.42
    賚
    0.41
    POSITIVE LOGITS
    ઢ
    0.94
    ਢ
    0.84
    ఢ
    0.80
    ढ
    0.79
    ڍ
    0.79
    ઢી
    0.79
    ढा
    0.75
    ଢ
    0.75
    ঢ
    0.75
    ඪ
    0.74
    Activations Density 0.003%

    No Known Activations