© 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. 152207
    Prev
    Next
    INDEX
    Explanations

    within percent or units

    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
     concession
    0.40
     Refunds
    0.36
     possèdent
    0.35
    ต่ำ
    0.35
     corresponden
    0.35
     retailing
    0.34
     inconvenience
    0.34
     下
    0.34
     fortune
    0.33
     concessions
    0.33
    POSITIVE LOGITS
    RAEL
    0.40
    godic
    0.39
    ogo
    0.37
    initial
    0.36
    ması
    0.36
    ills
    0.35
    acao
    0.35
    Inicial
    0.35
    להקה
    0.35
     සම
    0.35
    Activations Density 0.001%

    No Known Activations