© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 211813
    Prev
    Next
    INDEX
    Explanations

    VTuber / VTubing

    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_19_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
     OTT
    0.49
     Männer
    0.47
     सेवक
    0.46
     uomini
    0.46
     स्पोर्ट
    0.45
     Receivable
    0.45
     ಸೂಚ
    0.45
    ಛ
    0.45
     Réponses
    0.45
    視頻
    0.45
    POSITIVE LOGITS
    th
    0.42
    raine
    0.41
    darwin
    0.41
     собственно
    0.41
    unlock
    0.40
    hum
    0.40
    City
    0.39
    usine
    0.39
    m
    0.39
    handle
    0.38
    Activations Density 0.002%

    No Known Activations