© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86093
    Prev
    Next
    INDEX
    Explanations

    lung base

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_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
    ю
    0.42
    ↵
    0.33
    ل
    0.32
    eur
    0.31
     Anc
    0.31
    çon
    0.31
        
    0.31
    elves
    0.31
    ду
    0.31
    চিত
    0.31
    POSITIVE LOGITS
    മ്ബ
    0.35
    𝙉
    0.34
     والے
    0.34
    𒉣
    0.34
     चिन्ह
    0.33
    जेस्टिव
    0.33
    柾
    0.33
    Volunteer
    0.32
     pennies
    0.32
    ンテージ
    0.32
    Activations Density 0.004%

    No Known Activations