© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 198060
    Prev
    Next
    INDEX
    Explanations

    technical tools

    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
     Pok
    0.48
    ienti
    0.42
     !}{
    0.41
    okane
    0.41
    Tok
    0.40
    Pok
    0.40
     Stop
    0.39
    Pont
    0.39
     Ok
    0.39
    Tort
    0.39
    POSITIVE LOGITS
     hick
    0.42
    ປີ
    0.37
     flo
    0.37
    Sicilian
    0.36
    सिस
    0.36
     pensamientos
    0.36
    フロ
    0.36
    蚜
    0.35
     hins
    0.35
    विचार
    0.34
    Activations Density 0.009%

    No Known Activations