© 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. 202563
    Prev
    Next
    INDEX
    Explanations

    monitoring tools

    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
     Surg
    0.39
    ្វ
    0.39
    тент
    0.38
    bation
    0.38
    ্টিফি
    0.38
     HTMLSc
    0.38
     uop
    0.37
    #:
    0.37
     contato
    0.37
    zler
    0.37
    POSITIVE LOGITS
     PROCESS
    0.36
     கலா
    0.36
    講
    0.36
    มาย
    0.36
     needles
    0.35
    ╁
    0.35
    Bullets
    0.35
     जोन
    0.35
     needle
    0.35
     central
    0.34
    Activations Density 0.000%

    No Known Activations