© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 216823
    Prev
    Next
    INDEX
    Explanations

    compensation

    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_47_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
     Rover
    0.40
    소를
    0.40
     mesto
    0.40
    ugar
    0.39
    ameva
    0.38
     거
    0.38
     জায়
    0.38
    bucks
    0.38
     Correa
    0.37
    angkalan
    0.37
    POSITIVE LOGITS
    林
    0.40
     ét
    0.40
    onu
    0.39
     Ét
    0.37
    ADOC
    0.37
    GetObject
    0.37
    林的
    0.36
    ゑ
    0.36
    ättre
    0.36
     километ
    0.36
    Activations Density 0.001%

    No Known Activations