© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 609
    Prev
    Next
    INDEX
    Explanations

    speech-to-text

    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_40_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
     vipp
    0.38
     Mind
    0.38
    탐
    0.38
    \})
    0.37
     DOS
    0.36
     Exploration
    0.36
     PRIVATE
    0.36
     privaten
    0.36
     Hat
    0.36
     siz
    0.36
    POSITIVE LOGITS
    concurrent
    0.42
    Speech
    0.42
    texts
    0.38
    premium
    0.38
     speak
    0.38
    speak
    0.38
     رپورٹ
    0.37
    #%%
    0.36
    rende
    0.35
     texting
    0.35
    Activations Density 0.007%

    No Known Activations