© 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. 23868
    Prev
    Next
    INDEX
    Explanations

    giant

    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
     vari
    2.58
     Vari
    2.19
    Vari
    2.00
    vari
    1.95
    变
    1.72
    變
    1.64
     вари
    1.62
     변
    1.46
     biến
    1.46
    VARI
    1.38
    POSITIVE LOGITS
     giant
    1.95
    giant
    1.82
    Giant
    1.80
     Giant
    1.70
    巨
    1.30
     gigante
    1.18
     giants
    1.06
    giants
    1.03
     quantum
    0.96
     gigantes
    0.93
    Activations Density 0.015%

    No Known Activations