© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 137667
    Prev
    Next
    INDEX
    Explanations

    watch expect

    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_46_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
     forget
    0.42
     przeg
    0.41
    forget
    0.40
     بھول
    0.38
     przedstaw
    0.38
     вес
    0.38
    someone
    0.38
     :)
    0.38
    Someone
    0.37
     feedings
    0.37
    POSITIVE LOGITS
     Watch
    0.45
     WATCH
    0.44
     watched
    0.42
     expected
    0.40
    WATCH
    0.40
     Expect
    0.40
     watch
    0.40
     expecting
    0.40
    EMAN
    0.39
    orez
    0.39
    Activations Density 0.003%

    No Known Activations