© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13292
    Prev
    Next
    INDEX
    Explanations

    physicalism, materialism, properties

    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
    quedas
    0.44
    녔
    0.42
    érm
    0.41
     buoy
    0.41
     Jean
    0.40
    EPA
    0.39
    Bone
    0.39
     কলকাতায়
    0.38
     Quel
    0.38
     модель
    0.38
    POSITIVE LOGITS
    にい
    0.42
     materi
    0.38
    oger
    0.35
    renner
    0.35
    --;
    0.34
    ガード
    0.34
     Pfeiffer
    0.34
    TokenType
    0.34
     Piot
    0.33
     мах
    0.33
    Activations Density 0.016%

    No Known Activations