© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175158
    Prev
    Next
    INDEX
    Explanations

    rng, distribution, Mekong, tunnels

    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_20_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
     ставак
    0.45
    Odds
    0.44
     лигасы
    0.43
    칫
    0.43
    ड़ा
    0.43
     एक्सप्ले
    0.42
     विक्रे
    0.42
    ktCap
    0.42
     కాదు
    0.42
     slashed
    0.41
    POSITIVE LOGITS
    utor
    0.47
    錬
    0.46
     He
    0.43
     duro
    0.43
    ite
    0.42
     hardness
    0.42
    reso
    0.42
    ંટ
    0.42
    レ
    0.40
    he
    0.39
    Activations Density 0.000%

    No Known Activations