© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43654
    Prev
    Next
    INDEX
    Explanations

    Erdoğan, Turkish president, Telangana

    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_13_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
    aktoren
    0.55
    போ
    0.55
    UNK
    0.55
    apayati
    0.54
     Meinung
    0.54
     Tengah
    0.53
    Params
    0.52
    大
    0.52
    IDADE
    0.52
    ármaz
    0.51
    POSITIVE LOGITS
    yse
    0.56
     loung
    0.55
     chois
    0.54
     aches
    0.53
     eller
    0.52
     Catherine
    0.52
     entreprise
    0.52
     services
    0.51
     этой
    0.51
     utilisons
    0.51
    Activations Density 0.001%

    No Known Activations