© 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. 111719
    Prev
    Next
    INDEX
    Explanations

    oak variants

    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
    0
    1.17
     at
    1.11
     scintill
    1.02
    "
    0.98
     to
    0.97
     reimbursement
    0.95
     five
    0.93
    ר
    0.92
     on
    0.89
    好看
    0.89
    POSITIVE LOGITS
    of
    1.62
    ا
    1.34
    ě
    1.30
    ные
    1.28
    ні
    1.23
    ‌های
    1.21
    and
    1.20
    ap
    1.20
    ный
    1.20
    ના
    1.18
    Activations Density 0.001%

    No Known Activations