© 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. 441
    Prev
    Next
    INDEX
    Explanations

    rain

    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
     audible
    0.55
     AUD
    0.52
     слы
    0.51
     듣
    0.50
    Aud
    0.50
     auditory
    0.50
     mendengar
    0.49
     heard
    0.47
     hör
    0.47
     ауди
    0.47
    POSITIVE LOGITS
     Shining
    0.46
     rain
    0.45
     localObject
    0.40
     Pert
    0.40
    濺
    0.40
     dust
    0.39
     força
    0.39
     Schatten
    0.38
     vid
    0.37
     veins
    0.36
    Activations Density 0.159%

    No Known Activations