© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207949
    Prev
    Next
    INDEX
    Explanations

    right wing

    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_56_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
     far
    3.22
    far
    2.64
    Far
    2.28
     Far
    2.14
    远
    2.14
    遠
    2.11
     далеко
    1.89
     FAR
    1.86
     jauh
    1.84
    远远
    1.83
    POSITIVE LOGITS
    ashion
    0.38
    Ṛ
    0.36
     parties
    0.35
     setCurrent
    0.35
     image
    0.34
    мії
    0.34
    واں
    0.34
     enjoyed
    0.33
     বুকের
    0.32
    াধ্য
    0.32
    Activations Density 0.002%

    No Known Activations