© 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. 67307
    Prev
    Next
    INDEX
    Explanations

    Read

    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
    Craig
    0.42
     along
    0.40
    productive
    0.37
     productive
    0.36
    तरह
    0.36
    ب
    0.35
     humanidad
    0.35
     candidature
    0.35
    Berg
    0.34
    prod
    0.33
    POSITIVE LOGITS
     Pot
    0.42
    ilian
    0.42
    íl
    0.41
    ణి
    0.38
     olmadığını
    0.38
    Pot
    0.37
    菏
    0.37
    pot
    0.36
    الان
    0.36
     लक्षात
    0.36
    Activations Density 0.001%

    No Known Activations