© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 150169
    Prev
    Next
    INDEX
    Explanations

    experimentalexperimentationresearchprojectdeveloping

    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_23_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
    hers
    0.45
     homes
    0.43
    밂
    0.41
     rumah
    0.41
    ப்பன்
    0.41
     ಮನೆಯ
    0.39
    mama
    0.39
     hjem
    0.39
     घर
    0.38
    遞
    0.38
    POSITIVE LOGITS
    Parallel
    0.46
    Done
    0.46
    Deviation
    0.45
    Finale
    0.45
    refined
    0.43
    पुस्तक
    0.43
    experiment
    0.41
    Experiment
    0.40
    ทด
    0.40
    Import
    0.40
    Activations Density 0.007%

    No Known Activations