© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32433
    Prev
    Next
    INDEX
    Explanations

    perspective from specific countries

    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
     tín
    0.40
     හො
    0.40
     procure
    0.38
    㭉
    0.38
    ｪ
    0.38
     glam
    0.38
     whore
    0.38
    tap
    0.37
    設け
    0.37
    agu
    0.37
    POSITIVE LOGITS
     side
    1.03
     lado
    0.96
     côté
    0.96
     Side
    0.95
     طرف
    0.93
     стороны
    0.93
    side
    0.92
    側の
    0.89
    Side
    0.88
    侧
    0.88
    Activations Density 0.008%

    No Known Activations