© 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. 8661
    Prev
    Next
    INDEX
    Explanations

    pytorch nn.Linear

    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
     Kann
    0.22
    iole
    0.21
     bur
    0.21
     Bur
    0.21
     Imam
    0.20
     صدیق
    0.20
     게
    0.20
     Laplace
    0.20
    mes
    0.19
    embedded
    0.19
    POSITIVE LOGITS
     گوئیاں
    0.25
    continued
    0.22
     زوج
    0.21
    راضي
    0.21
     continú
    0.20
     क्रिया
    0.20
     overturned
    0.20
    +}^{
    0.20
    زم
    0.20
    liance
    0.20
    Activations Density 0.002%

    No Known Activations