© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231290
    Prev
    Next
    INDEX
    Explanations

    high up

    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_6_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
    2
    1.40
    ’
    1.38
    n
    1.20
    op
    1.10
    3
    1.07
    ami
    1.00
    that
    1.00
    ath
    1.00
    ου
    0.98
     allemand
    0.97
    POSITIVE LOGITS
    ی
    0.88
     مو
    0.86
     ñ
    0.86
     apă
    0.85
     ś
    0.84
     ı
    0.83
     vínculo
    0.82
    中
    0.82
     manera
    0.80
     presenceData
    0.80
    Activations Density 0.000%

    No Known Activations