© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 47377
    Prev
    Next
    INDEX
    Explanations

    road trip Radio

    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_10_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
    ная
    0.63
     evidentemente
    0.63
     eine
    0.57
    gegeben
    0.55
    hesia
    0.53
    ハ
    0.51
     mehrere
    0.51
     uma
    0.50
     een
    0.50
    spieler
    0.50
    POSITIVE LOGITS
     choosing
    0.61
     correlated
    0.58
     इफ
    0.47
     Cognitive
    0.47
     BETTER
    0.47
     வேற
    0.47
     दैट
    0.47
     Choosing
    0.46
    حم
    0.46
    ¹
    0.46
    Activations Density 0.000%

    No Known Activations