© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 139495
    Prev
    Next
    INDEX
    Explanations

    redirect user

    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
    から
    0.46
    ຟ
    0.38
     από
    0.38
     Password
    0.37
    quote
    0.37
     Pes
    0.36
     کہنا
    0.36
    from
    0.36
     dialog
    0.36
     Portrait
    0.35
    POSITIVE LOGITS
    ﻈ
    0.43
    ऐ
    0.42
     reach
    0.41
    واد
    0.40
    Kali
    0.40
    よいよ
    0.39
     отношению
    0.38
    Programa
    0.38
    看到
    0.37
     বৃত্তি
    0.37
    Activations Density 0.004%

    No Known Activations