© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89596
    Prev
    Next
    INDEX
    Explanations

    Abrams, tanks, park, mbembe

    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_3_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
     I
    0.91
     It
    0.77
    กับ
    0.66
    }
    0.62
     D
    0.60
    í
    0.59
     A
    0.59
    就
    0.58
    ﻮ
    0.58
     Conversations
    0.57
    POSITIVE LOGITS
    م
    0.75
    ни
    0.73
    ان
    0.71
    ش
    0.70
     commande
    0.66
     θα
    0.65
     nourr
    0.65
    ج
    0.64
     mètre
    0.64
    м
    0.64
    Activations Density 0.000%

    No Known Activations