© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205795
    Prev
    Next
    INDEX
    Explanations

    intended

    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_56_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
     suivante
    0.41
    ácie
    0.41
     التالية
    0.40
     suivants
    0.39
     llevando
    0.37
     recognising
    0.37
    苃
    0.37
     wandered
    0.36
     التالي
    0.36
     committing
    0.36
    POSITIVE LOGITS
     только
    0.37
    டெ
    0.37
     NSString
    0.37
    至
    0.36
     aisa
    0.36
     জ্ব
    0.36
     ڈاک
    0.36
     to
    0.35
     throughout
    0.35
     efektif
    0.35
    Activations Density 0.004%

    No Known Activations