© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82783
    Prev
    Next
    INDEX
    Explanations

    the

    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_53_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
    ritus
    0.43
    με
    0.39
    နဲ့
    0.38
    
    0.38
     mest
    0.38
    侙
    0.38
    மை
    0.37
    Ber
    0.37
     বস
    0.37
    假期
    0.37
    POSITIVE LOGITS
     WF
    0.38
     wchar
    0.38
     Vf
    0.37
    சனம்
    0.36
    寒
    0.35
     wf
    0.35
    ilibus
    0.35
    Coref
    0.35
    orrag
    0.34
    哗
    0.33
    Activations Density 0.001%

    No Known Activations