© 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. 227415
    Prev
    Next
    INDEX
    Explanations

    CP, FID, CLS

    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
    ת
    1.75
    at
    1.28
    ב
    1.28
    أ
    1.18
    "
    1.15
    การ
    1.09
     It
    1.09
    A
    1.00
    י
    0.99
    B
    0.98
    POSITIVE LOGITS
    duit
    1.03
    ifting
    1.01
    ndrome
    0.99
    ndvi
    0.96
    ‌هایی
    0.95
     რომლებიც
    0.93
    mtr
    0.92
    rezent
    0.92
    mination
    0.91
    kde
    0.91
    Activations Density 0.000%

    No Known Activations