© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58988
    Prev
    Next
    INDEX
    Explanations

    pronunciation of sounds

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     s
    0.51
     ä
    0.47
     b
    0.46
     k
    0.45
     t
    0.43
     अ
    0.42
     ма
    0.42
     mActivity
    0.41
     m
    0.41
     ml
    0.41
    POSITIVE LOGITS
     -
    0.41
    sn
    0.39
    san
    0.39
    sph
    0.39
    –
    0.39
    are
    0.39
    s
    0.39
     –
    0.38
     Are
    0.37
    ESP
    0.37
    Activations Density 0.005%

    No Known Activations