© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 6481
    Prev
    Next
    INDEX
    Explanations

    cricket

    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_44_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
    σσ
    0.39
    벳
    0.38
    Logic
    0.38
    婪
    0.36
    װ
    0.36
    sciutto
    0.35
     সাস
    0.35
    }(-\
    0.35
     হইয়
    0.34
    astr
    0.34
    POSITIVE LOGITS
     counter
    0.43
     unión
    0.40
     fifth
    0.38
    煊
    0.37
     Reverse
    0.37
    ガラ
    0.37
     disrupting
    0.36
     unification
    0.36
     cur
    0.36
     disrupt
    0.36
    Activations Density 0.002%

    No Known Activations