© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 89360
    Prev
    Next
    INDEX
    Explanations

    Russian descriptors

    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_60_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
     mert
    0.45
     globalisation
    0.43
     organiser
    0.43
     ని
    0.40
     specialised
    0.40
     utilises
    0.40
     बै
    0.39
     ఇ
    0.39
    aren
    0.38
     civilisation
    0.38
    POSITIVE LOGITS
    ної
    1.23
    ny
    1.16
    nym
    1.05
    NY
    1.05
    ны
    1.03
    Ny
    0.98
    ную
    0.93
    ной
    0.93
    ною
    0.89
    но
    0.88
    Activations Density 0.003%

    No Known Activations