© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 47123
    Prev
    Next
    INDEX
    Explanations

    code segments and code-related terms

    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_10_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
    կ
    0.55
     entfer
    0.53
    բ
    0.48
    ﻜ
    0.48
    տ
    0.47
    บ
    0.45
    <unused2133>
    0.45
     γνωσ
    0.45
     μαγγ
    0.45
    <unused2150>
    0.45
    POSITIVE LOGITS
    Wireless
    0.53
     informativa
    0.52
    Fits
    0.51
    Option
    0.49
    Use
    0.48
    Buying
    0.48
    PersonalInfo
    0.48
     Sunak
    0.48
    Swimming
    0.47
    Congratulations
    0.46
    Activations Density 0.000%

    No Known Activations