© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 65398
    Prev
    Next
    INDEX
    Explanations

    environmental events

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    iletto
    0.48
     Hyundai
    0.41
    Hyundai
    0.41
    諫
    0.38
     Stratford
    0.37
    史
    0.37
     Toto
    0.37
    AVAILABLE
    0.37
     Helio
    0.37
     Huy
    0.36
    POSITIVE LOGITS
    Bomb
    0.47
    OCE
    0.45
    爆
    0.43
    Ocean
    0.42
     Typh
    0.40
    Earth
    0.40
     Зем
    0.40
     Bomb
    0.39
    Env
    0.39
     ambientales
    0.39
    Activations Density 0.000%

    No Known Activations