© 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. 234352
    Prev
    Next
    INDEX
    Explanations

    0Method 1The MAX_ACTIVATING_TOKENS are all the same token (0).0

    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
    枥
    0.43
    мого
    0.39
    tren
    0.37
    นะนำ
    0.36
     Steph
    0.36
    㛲
    0.35
    молу
    0.35
    iri
    0.35
    ቄ
    0.35
    ران
    0.34
    POSITIVE LOGITS
     Desenvolvimento
    0.40
     Sole
    0.39
     Fingers
    0.38
     رکھیں
    0.37
     když
    0.37
     wid
    0.37
    Thumb
    0.36
    十年
    0.35
     vork
    0.35
    sufficiency
    0.35
    Activations Density 0.001%

    No Known Activations