© 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
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198604
    Prev
    Next
    INDEX
    Explanations

    informal greetings

    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
     glab
    0.42
     Longitudinal
    0.39
    脚
    0.39
    憬
    0.38
    omores
    0.38
     পেট
    0.36
    encana
    0.36
    tend
    0.36
     পে
    0.35
    arrays
    0.35
    POSITIVE LOGITS
     Piso
    0.39
     connect
    0.39
     हैप्पी
    0.37
    Diesel
    0.36
     વધી
    0.36
     باذن
    0.35
    谶
    0.35
     সংযোগ
    0.35
    чала
    0.35
    (".")
    0.34
    Activations Density 0.000%

    No Known Activations