© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 240597
    Prev
    Next
    INDEX
    Explanations

    sounds like

    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_25_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
     назна
    0.41
    назна
    0.40
    Signed
    0.40
    Designed
    0.39
     използ
    0.39
    啷
    0.39
     customarily
    0.38
     придума
    0.38
    Philipp
    0.38
    Traditionally
    0.38
    POSITIVE LOGITS
    ژ
    0.40
    čkog
    0.38
    ächst
    0.37
    oty
    0.37
     rufis
    0.37
    egaard
    0.37
    浮
    0.37
    θεί
    0.36
    θ
    0.36
    িপি
    0.35
    Activations Density 0.003%

    No Known Activations