© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219944
    Prev
    Next
    INDEX
    Explanations

    cost ranges and amounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    itamos
    0.38
     पूछी
    0.36
    〢
    0.34
     conservatively
    0.34
     প্যার
    0.33
    ียด
    0.33
     ملین
    0.33
     moneys
    0.33
     levied
    0.33
     বিজ্ঞাপন
    0.33
    POSITIVE LOGITS
    罕
    0.36
     ramps
    0.36
    Ofer
    0.36
    offer
    0.35
     Gregorio
    0.35
     Gren
    0.35
     pocas
    0.35
    炜
    0.35
    اوی
    0.35
    NavItem
    0.34
    Activations Density 0.004%

    No Known Activations