© 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. 63330
    Prev
    Next
    INDEX
    Explanations

    dill

    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
    pha
    0.39
     Corbett
    0.38
    菡
    0.38
     ENV
    0.37
     উন্নয়ন
    0.37
     Correa
    0.37
     विकास
    0.36
     Bruno
    0.36
     opinion
    0.36
     Alina
    0.36
    POSITIVE LOGITS
     dill
    0.50
    莳
    0.42
    starts
    0.42
    excluding
    0.41
    Starts
    0.41
     डिल
    0.41
    Chez
    0.40
     Dill
    0.40
    exclusion
    0.39
     شوید
    0.39
    Activations Density 0.012%

    No Known Activations