© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10983
    Prev
    Next
    INDEX
    Explanations

    marks and dashes

    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_13_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
    <h3>
    0.59
     Raphael
    0.55
    <code>
    0.53
     `./
    0.53
    rschein
    0.52
    ermeister
    0.51
    ulman
    0.51
    deut
    0.50
    <h4>
    0.49
     />
    0.49
    POSITIVE LOGITS
    ﻬ
    0.60
    ﻔ
    0.58
    Bluetooth
    0.56
    Wireless
    0.56
    EOUT
    0.55
     empieza
    0.55
     تعریف
    0.55
     fios
    0.55
     farmac
    0.54
    Loops
    0.54
    Activations Density 0.026%

    No Known Activations