© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134948
    Prev
    Next
    INDEX
    Explanations

    Halcon, Hawk, Hills, arsis

    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_6_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
    ,
    1.09
    м
    0.82
    +](=
    0.82
     pasal
    0.79
    ים
    0.78
     misuse
    0.78
     workstation
    0.78
    アカウント
    0.75
     handshake
    0.74
     sizin
    0.73
    POSITIVE LOGITS
    ك
    0.98
    Про
    0.94
    يد
    0.93
    for
    0.91
    Y
    0.90
     Și
    0.87
    Мо
    0.86
    ován
    0.86
    ोर
    0.86
    في
    0.86
    Activations Density 0.000%

    No Known Activations