© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 205322
    Prev
    Next
    INDEX
    Explanations

    inflation

    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
    reibt
    0.41
     strolled
    0.39
     softwood
    0.35
    cedes
    0.35
    מיני
    0.35
    स्फ
    0.35
    }^{*}=\
    0.35
     '=',
    0.34
     decouple
    0.34
     Aye
    0.34
    POSITIVE LOGITS
     age
    0.52
    age
    0.46
     Age
    0.46
    Age
    0.44
    IamPolicy
    0.42
     tailored
    0.41
    gangenheit
    0.40
     Tail
    0.38
    年月
    0.38
     tailor
    0.38
    Activations Density 0.000%

    No Known Activations