© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 233430
    Prev
    Next
    INDEX
    Explanations

    sounds and imitation

    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_32_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
    Sound
    0.55
    sound
    0.51
    吱
    0.50
    Noise
    0.49
     sque
    0.46
    响
    0.46
     noises
    0.46
    friction
    0.46
     noise
    0.45
     nois
    0.45
    POSITIVE LOGITS
    ้อม
    0.47
     plomb
    0.44
     cuticle
    0.42
     skull
    0.40
    掐
    0.38
     borough
    0.38
    髪
    0.38
     constaté
    0.38
    OMB
    0.38
     skulls
    0.38
    Activations Density 0.006%

    No Known Activations