© 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. 20114
    Prev
    Next
    INDEX
    Explanations

    Russian first-person

    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
     пар
    0.41
     Observing
    0.37
     GU
    0.36
     Rough
    0.36
     gu
    0.35
     गु
    0.35
     '//
    0.35
     Focusing
    0.34
     responsible
    0.34
     დ
    0.34
    POSITIVE LOGITS
     ich
    0.52
     считаю
    0.48
     Ich
    0.45
    Ich
    0.44
    ich
    0.44
     tomo
    0.43
    iche
    0.42
    ICH
    0.42
     сегодня
    0.42
     उनके
    0.41
    Activations Density 0.012%

    No Known Activations