© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 178225
    Prev
    Next
    INDEX
    Explanations

    joined by

    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_24_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
     parallels
    0.39
    =/
    0.36
     космо
    0.36
     ceremony
    0.35
     चलो
    0.35
     COMMENT
    0.34
     пере
    0.34
     другой
    0.34
    spac
    0.34
     человека
    0.33
    POSITIVE LOGITS
     Saves
    0.44
     Foot
    0.42
    utile
    0.42
    鋈
    0.41
    蚋
    0.40
     Locks
    0.39
    ితే
    0.39
     २४
    0.39
    Vul
    0.39
     бясплат
    0.39
    Activations Density 0.000%

    No Known Activations