© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179636
    Prev
    Next
    INDEX
    Explanations

    releases, leak, secrete

    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_24_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
     Adresse
    0.46
    Я
    0.44
     яв
    0.43
    يا
    0.41
     जीतकर
    0.41
    ヤモンド
    0.40
     caractères
    0.39
     Geschäfts
    0.39
     Bahasa
    0.39
    ﻴ
    0.39
    POSITIVE LOGITS
     insulate
    0.48
     beam
    0.43
     garlands
    0.43
     secrete
    0.42
     garland
    0.40
     necessitate
    0.40
     leak
    0.40
     Moment
    0.40
     subcut
    0.39
     beams
    0.39
    Activations Density 0.000%

    No Known Activations