© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102070
    Prev
    Next
    INDEX
    Explanations

    pointing to

    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_14_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
    istice
    0.53
    Site
    0.51
     vostra
    0.50
     impoverished
    0.49
    ﺎ
    0.49
     finestra
    0.49
    OSITION
    0.49
     Illustrator
    0.48
     openc
    0.48
    US
    0.47
    POSITIVE LOGITS
     mudd
    0.51
    荃灣
    0.45
    sentiment
    0.43
    ടതി
    0.43
    डि
    0.43
    骧
    0.42
    嘉宾
    0.41
     چاہ
    0.41
    まり
    0.40
    денти
    0.40
    Activations Density 0.000%

    No Known Activations