© 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
    2. Gemma-3-27B-IT
    3. 60-GEMMASCOPE-2-TRANSCODER-262K
    4. 152895
    Prev
    Next
    INDEX
    Explanations

    sounds and noises

    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_60_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
     noises
    1.45
    一声
    0.46
    rolls
    0.40
     nois
    0.40
     noisy
    0.38
     声
    0.37
     bunyi
    0.37
    alphas
    0.36
    了一声
    0.36
    ésil
    0.35
    POSITIVE LOGITS
     No
    0.65
    no
    0.61
     ring
    0.58
    No
    0.57
     Ring
    0.50
    効果
    0.47
    の効果
    0.44
     animal
    0.44
    悲
    0.43
     car
    0.42
    Activations Density 0.037%

    No Known Activations