© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 156569
    Prev
    Next
    INDEX
    Explanations

    names and technical terms

    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_50_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
    శు
    0.41
    וש
    0.41
    Lad
    0.40
    ណ្
    0.37
     suc
    0.37
    AMO
    0.36
    ᓗ
    0.36
    juč
    0.36
     succ
    0.35
    Fred
    0.35
    POSITIVE LOGITS
    蕈
    0.40
     Ger
    0.38
     অচেতন
    0.37
     Scoop
    0.37
    AppCompatTheme
    0.37
     ಗ್ರಾ
    0.37
     anna
    0.36
     Thirty
    0.36
    ElementException
    0.36
     Clint
    0.36
    Activations Density 0.006%

    No Known Activations