© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111649
    Prev
    Next
    INDEX
    Explanations

    cyrillic prefix + 'na' or 'international'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    s
    1.41
    3
    1.34
    d
    1.26
    ps
    1.16
    ي
    1.13
    ς
    1.13
    _
    1.12
    st
    1.11
    తో
    1.05
    2
    1.05
    POSITIVE LOGITS
    im
    1.20
     ofreci
    1.09
     aceptar
    1.08
    imizi
    1.04
    ામ
    1.02
     incrementar
    1.02
     compito
    1.02
     enviar
    1.01
     atteint
    1.00
     asignar
    0.98
    Activations Density 0.000%

    No Known Activations