© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 238097
    Prev
    Next
    INDEX
    Explanations

    sparse categorical crossentropy

    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_25_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
    oplastic
    0.26
     histologic
    0.25
    丂
    0.23
    Foods
    0.23
    oua
    0.22
    ього
    0.22
     Planta
    0.22
     wholeheartedly
    0.22
     Calc
    0.22
     Marlin
    0.22
    POSITIVE LOGITS
    lys
    0.26
    rights
    0.25
    hum
    0.24
    rashed
    0.24
    Ϳ
    0.24
    create
    0.24
    assung
    0.24
     فهر
    0.24
     hochwert
    0.24
    ustes
    0.24
    Activations Density 0.004%

    No Known Activations