© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79583
    Prev
    Next
    INDEX
    Explanations

    time, duration, periods

    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_0_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
    y
    1.55
    ر
    1.53
    to
    1.49
    ли
    1.48
    eers
    1.47
    4
    1.46
     जिससे
    1.44
    a
    1.44
    ม
    1.44
    ur
    1.38
    POSITIVE LOGITS
    ě
    1.40
     It
    1.24
     ampia
    1.23
    </b>
    1.16
     размеры
    1.12
    ட்சத்திர
    1.06
    <0x0D>
    1.05
    ું
    1.05
    पणे
    1.05
    </h2>
    1.03
    Activations Density 0.000%

    No Known Activations