© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 218375
    Prev
    Next
    INDEX
    Explanations

    non-custodial protocol validation

    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_16_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
    helpTool
    0.44
    "-------
    0.44
    一致
    0.43
     మరింత
    0.42
     hesitated
    0.42
    🌓
    0.42
    ziel
    0.41
    兴趣
    0.41
     hesitation
    0.41
    重新
    0.40
    POSITIVE LOGITS
    ла
    0.61
    िओ
    0.50
    ओ
    0.48
    ни
    0.48
    ти
    0.47
     тө
    0.47
     amis
    0.47
    amnă
    0.47
    ar
    0.47
     nilai
    0.47
    Activations Density 0.000%

    No Known Activations