© 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. 134904
    Prev
    Next
    INDEX
    Explanations

    getting directions

    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
    ല
    0.93
    ار
    0.91
     horizont
    0.85
    نا
    0.84
     الآخر
    0.84
    ור
    0.83
    ল
    0.83
    ва
    0.81
    )，
    0.80
    وين
    0.80
    POSITIVE LOGITS
    ı
    1.27
    a
    1.23
    to
    1.18
    ти
    1.02
    ی
    1.00
    li
    0.94
    s
    0.94
    æ
    0.90
    arian
    0.88
    ัก
    0.88
    Activations Density 0.002%

    No Known Activations