© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46720
    Prev
    Next
    INDEX
    Explanations

    tennis court

    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_13_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
    f
    0.70
    4
    0.61
    5
    0.60
    6
    0.59
    를
    0.55
    loans
    0.53
    al
    0.53
    9
    0.53
    1
    0.51
    3
    0.51
    POSITIVE LOGITS
     PM
    0.57
     их
    0.55
     Konstru
    0.55
     kulturn
    0.54
     silico
    0.53
     gesam
    0.52
     U
    0.51
    嬠
    0.51
    полни
    0.51
     Kultur
    0.50
    Activations Density 0.000%

    No Known Activations