© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23675
    Prev
    Next
    INDEX
    Explanations

    say Russian endings

    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_56_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
    ю
    0.43
    НИЕ
    0.37
    дан
    0.36
    ние
    0.36
    STY
    0.36
    регистри
    0.36
    пере
    0.35
    ведении
    0.35
    িয়
    0.35
    ним
    0.34
    POSITIVE LOGITS
    자
    1.39
     потому
    1.04
     Потому
    0.94
     because
    0.93
    者
    0.87
    Because
    0.82
     porque
    0.80
    ного
    0.80
    者の
    0.80
    ers
    0.79
    Activations Density 0.015%

    No Known Activations