© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45838
    Prev
    Next
    INDEX
    Explanations

    automatic identification and speech recognition

    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_3_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
     (
    0.74
    was
    0.73
     Senin
    0.64
     [
    0.63
     was
    0.62
    ']
    0.61
     personaje
    0.60
    REME
    0.59
     oso
    0.58
     iban
    0.57
    POSITIVE LOGITS
     ک
    0.84
     کر
    0.81
    ur
    0.75
    ages
    0.75
    homes
    0.66
    bikes
    0.64
     добав
    0.64
    mét
    0.63
    লি
    0.63
    autom
    0.62
    Activations Density 0.005%

    No Known Activations