© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2609
    Prev
    Next
    INDEX
    Explanations

    'use strict';

    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_40_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
     कायदा
    0.45
    LAW
    0.40
     закона
    0.38
    䙷
    0.38
     LAW
    0.38
     ラン
    0.37
    ጉ
    0.37
    ተት
    0.35
    ╞
    0.35
     pháp
    0.35
    POSITIVE LOGITS
     सख्त
    0.55
    Hard
    0.53
     stricter
    0.52
     कठोर
    0.52
    硬
    0.51
     hardness
    0.47
     Hard
    0.47
     tougher
    0.46
    严
    0.46
     hard
    0.46
    Activations Density 0.001%

    No Known Activations