© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195749
    Prev
    Next
    INDEX
    Explanations

    AI responses

    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_50_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
    cont
    0.44
    ábado
    0.43
    <0xAC>
    0.42
     obeys
    0.39
     آبادی
    0.39
    cinoma
    0.36
    욘
    0.36
    sides
    0.36
     आंगन
    0.36
     اله
    0.36
    POSITIVE LOGITS
     alp
    0.41
     gastron
    0.41
    შინ
    0.40
     Alp
    0.40
     labb
    0.38
    ﻏ
    0.38
    tfine
    0.37
     Ghaz
    0.37
     TFT
    0.36
     lack
    0.36
    Activations Density 0.000%

    No Known Activations