© 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. 176448
    Prev
    Next
    INDEX
    Explanations

    faith

    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
    Mole
    0.42
    iosa
    0.40
     B
    0.40
    angu
    0.40
     Metern
    0.39
     informe
    0.38
    mets
    0.38
     Informe
    0.38
    mij
    0.38
    phs
    0.38
    POSITIVE LOGITS
    াবেক
    0.38
    <unused6>
    0.37
    ້ອຍ
    0.36
    జ్‌
    0.35
    纳
    0.35
    дово
    0.35
    嬂
    0.34
    埴
    0.34
     Vul
    0.33
     వర
    0.33
    Activations Density 0.000%

    No Known Activations