© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86577
    Prev
    Next
    INDEX
    Explanations

    custom/first followed by descriptor

    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_3_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
    ﺮ
    1.02
    ަލ
    1.00
    리
    0.99
    ли
    0.97
    Ко
    0.83
    ል።
    0.79
    ﻮ
    0.79
    ン
    0.77
     Moldova
    0.76
    نك
    0.75
    POSITIVE LOGITS
    at
    1.12
    </h3>
    0.71
    ’
    0.71
    otis
    0.66
    ants
    0.66
                    
    0.65
     editors
    0.65
    0.62
     i
    0.61
    utors
    0.61
    Activations Density 0.008%

    No Known Activations