© 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. 31219
    Prev
    Next
    INDEX
    Explanations

    loud vocalizations

    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
     laugh
    0.46
     laughed
    0.40
    㭐
    0.40
     laughs
    0.39
     gall
    0.38
     voice
    0.36
     laughing
    0.36
     grove
    0.36
     Laugh
    0.36
     belle
    0.36
    POSITIVE LOGITS
     "!
    0.43
     refle
    0.41
    ″]
    0.40
    হইল
    0.40
     ".
    0.39
     “.
    0.38
     ”.
    0.38
    setInt
    0.37
    சையில்
    0.35
    細菌
    0.35
    Activations Density 0.008%

    No Known Activations