© 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. 196984
    Prev
    Next
    INDEX
    Explanations

    easy

    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
     ਤ
    0.38
    zers
    0.38
    zert
    0.37
     थिंक
    0.36
     Stability
    0.36
     Knowledge
    0.36
    estruct
    0.35
     hearth
    0.35
     बेटर
    0.35
    ichert
    0.34
    POSITIVE LOGITS
     pe
    0.56
     breezy
    0.55
     d
    0.53
     pants
    0.53
     Pe
    0.49
     PE
    0.44
    PE
    0.42
    Pe
    0.42
     д
    0.42
    хии
    0.41
    Activations Density 0.002%

    No Known Activations