© 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. 205941
    Prev
    Next
    INDEX
    Explanations

    wildlife

    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
     granted
    0.43
    вані
    0.39
    жные
    0.38
    granted
    0.37
    venor
    0.37
     असह
    0.37
    単位
    0.36
    鼍
    0.36
    ঘু
    0.35
     geese
    0.35
    POSITIVE LOGITS
    throw
    0.41
     Shub
    0.38
     बृह
    0.37
     Kub
    0.37
     बेहत
    0.36
     혼
    0.36
     भूषण
    0.36
     बृ
    0.36
    THROW
    0.36
    𝚢
    0.36
    Activations Density 0.000%

    No Known Activations