© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207150
    Prev
    Next
    INDEX
    Explanations

    Communism

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    ض
    0.39
    neas
    0.38
    छा
    0.38
    Conflicts
    0.37
     SUBS
    0.37
    ئة
    0.36
    Ⅺ
    0.36
    ﻨ
    0.36
    Ꮩ
    0.35
    ਜ਼
    0.35
    POSITIVE LOGITS
    als
    0.65
    al
    0.59
    ally
    0.57
    ाल
    0.53
    ALS
    0.53
     Party
    0.52
     party
    0.51
     પાર્ટી
    0.50
    AL
    0.49
    াল
    0.49
    Activations Density 0.000%

    No Known Activations