© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 178247
    Prev
    Next
    INDEX
    Explanations

    Russian/Ukrainian words

    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_50_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
    scrollY
    0.48
     Ха
    0.45
    Gir
    0.44
     Gir
    0.44
     गिर
    0.43
     bộ
    0.43
    யம்
    0.42
    海
    0.42
    Hal
    0.41
     ह
    0.40
    POSITIVE LOGITS
    olo
    0.42
     पद्
    0.40
    OLO
    0.39
    olz
    0.38
    iling
    0.38
    rte
    0.37
    を見る
    0.37
    RT
    0.36
    ILING
    0.36
    rt
    0.36
    Activations Density 0.000%

    No Known Activations