© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78003
    Prev
    Next
    INDEX
    Explanations

    Lithuanian language context

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
    фикации
    0.43
     پار
    0.42
     விச
    0.40
     Pok
    0.38
     παρα
    0.38
    敺
    0.38
    Kit
    0.37
     Reaction
    0.37
     VERT
    0.37
     Kit
    0.36
    POSITIVE LOGITS
     p
    0.45
    rode
    0.43
    浆
    0.43
    SUN
    0.41
    iges
    0.40
    quement
    0.38
    ल्पन
    0.38
    OCKED
    0.38
    portivo
    0.37
    Sus
    0.37
    Activations Density 0.000%

    No Known Activations