© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126790
    Prev
    Next
    INDEX
    Explanations

    Indium Tin Oxide and FTO

    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_37_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
     voice
    0.74
     voix
    0.58
     صوت
    0.58
    嗓
    0.58
    Voice
    0.57
     voce
    0.57
    voice
    0.56
     Voice
    0.55
     Stimme
    0.54
     VOICE
    0.53
    POSITIVE LOGITS
    ವಾರ
    0.38
    跎
    0.38
    Shen
    0.37
    শায়
    0.37
     }),
    0.36
    Bast
    0.36
    쑥
    0.36
    上げて
    0.36
     Bast
    0.35
    Ellis
    0.35
    Activations Density 0.001%

    No Known Activations