© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 249426
    Prev
    Next
    INDEX
    Explanations

    the letter F

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     p
    1.16
    微
    1.13
     ми
    1.03
     미
    1.00
     мі
    0.95
    meas
    0.95
     微
    0.86
     mik
    0.86
    미
    0.83
    Mik
    0.82
    POSITIVE LOGITS
     meager
    0.96
     meagre
    0.89
     paltry
    0.64
     feeble
    0.38
     সর্বনিম্ন
    0.37
    ран
    0.35
     cendré
    0.35
     scanty
    0.35
     পলিপ
    0.35
    谪
    0.34
    Activations Density 0.002%

    No Known Activations