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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60047
    Prev
    Next
    INDEX
    Explanations

    application

    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_11_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
    АС
    0.52
    ڈ
    0.52
     Enemy
    0.49
     شدہ
    0.47
     Normalmente
    0.47
    Фі
    0.47
    烦
    0.47
     diversi
    0.46
    ન્ટ
    0.46
    भ
    0.46
    POSITIVE LOGITS
     shoreline
    0.47
    pore
    0.47
    rail
    0.45
    ha
    0.45
    waarden
    0.45
    lattice
    0.43
     pounding
    0.43
     dyeing
    0.43
    lock
    0.42
     line
    0.41
    Activations Density 0.009%

    No Known Activations