© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110492
    Prev
    Next
    INDEX
    Explanations

    dor, dorf, dojo

    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
    та
    1.27
    <0x0D>
    1.18
    od
    1.13
    ار
    1.12
    is
    1.02
    的声音
    1.02
     PLN
    1.01
     Quindi
    0.98
     UBND
    0.98
    的效果
    0.97
    POSITIVE LOGITS
    ك
    1.48
    ка
    1.37
    ning
    1.29
    se
    1.28
    و
    1.24
    み
    1.24
    م
    1.20
    خ
    1.20
    ה
    1.20
    ор
    1.17
    Activations Density 0.000%

    No Known Activations