© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 198038
    Prev
    Next
    INDEX
    Explanations

    russian and hungarian words

    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_27_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
    ‌‌
    0.44
     წარ
    0.42
     প্রদেশ
    0.41
    莞
    0.41
    曈
    0.38
     Gd
    0.37
    ┄
    0.37
    <unused2125>
    0.37
     Hồ
    0.37
    푯
    0.37
    POSITIVE LOGITS
    RC
    0.41
    rypt
    0.40
     Championship
    0.38
    ag
    0.37
     counted
    0.37
    RS
    0.37
    RH
    0.37
    ad
    0.36
    aiya
    0.36
    adi
    0.36
    Activations Density 0.001%

    No Known Activations