© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 260716
    Prev
    Next
    INDEX
    Explanations

    strike price

    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_5_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
    ”
    1.06
     A
    1.03
    )
    1.00
    Y
    0.98
     I
    0.97
    5
    0.97
    ’
    0.94
    of
    0.92
     âm
    0.91
    ท
    0.90
    POSITIVE LOGITS
     Хабаровского
    1.32
     Фурга
    1.30
    ان
    1.23
     Функ
    1.18
    م
    1.05
    ds
    1.03
    tements
    1.03
    jera
    1.03
    funcion
    1.03
    jším
    1.03
    Activations Density 0.005%

    No Known Activations