© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59011
    Prev
    Next
    INDEX
    Explanations

    Hungarian names/places

    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_2_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
    し
    1.13
    at
    1.12
    oje
    0.95
    lø
    0.92
    um
    0.91
    jší
    0.91
    将
    0.89
    ться
    0.89
    bred
    0.88
    toare
    0.88
    POSITIVE LOGITS
    ﻛ
    0.93
    э
    0.92
     поверхности
    0.91
    ра
    0.90
    ин
    0.89
    ),
    0.88
    ين
    0.88
    (),
    0.86
    스의
    0.86
    ев
    0.84
    Activations Density 0.001%

    No Known Activations