© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 197885
    Prev
    Next
    INDEX
    Explanations

    definitions and specifications

    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_9_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
     kil
    0.52
    )>
    0.50
     a
    0.50
    上面
    0.49
     nên
    0.48
     picky
    0.48
     Akhtar
    0.47
     cla
    0.47
     numerator
    0.47
    :
    0.47
    POSITIVE LOGITS
    ids
    0.52
    帰
    0.47
     شرق
    0.45
    itions
    0.43
    enteuer
    0.43
    lications
    0.42
    centric
    0.42
    spiele
    0.42
     impacts
    0.42
    iej
    0.42
    Activations Density 0.000%

    No Known Activations