© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129980
    Prev
    Next
    INDEX
    Explanations

    conspiracy theories

    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_1_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
    ли
    1.24
    jší
    1.16
    ;
    1.12
    _
    1.11
    ﻗ
    0.97
     и
    0.93
    },
    0.90
    forcement
    0.90
     июня
    0.90
     وي
    0.90
    POSITIVE LOGITS
    u
    1.30
    s
    1.18
    ing
    1.15
    ת
    1.06
    ش
    1.02
    ل
    1.02
    ன்
    0.95
    ER
    0.94
    rs
    0.94
    ع
    0.92
    Activations Density 0.000%

    No Known Activations