© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80754
    Prev
    Next
    INDEX
    Explanations

    SES abbreviation

    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_0_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
    8
    1.84
    4
    1.66
     are
    1.56
    7
    1.54
    9
    1.47
    w
    1.45
    ne
    1.43
    6
    1.40
    5
    1.33
    ")
    1.30
    POSITIVE LOGITS
    s
    1.38
     consignment
    1.27
    τε
    1.26
    ли
    1.25
     covalent
    1.25
     transgress
    1.25
    ก
    1.25
     wrongdoing
    1.24
     centrifugal
    1.21
     insuff
    1.19
    Activations Density 0.000%

    No Known Activations