© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 214298
    Prev
    Next
    INDEX
    Explanations

    questions/communications

    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_16_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
    4
    0.59
    Lewis
    0.56
    ell
    0.55
     Ing
    0.55
     Orr
    0.53
     Enchant
    0.52
     Wand
    0.51
    9
    0.51
     Quar
    0.50
    Fone
    0.50
    POSITIVE LOGITS
     recuperar
    0.51
     gambling
    0.49
     banc
    0.49
     يد
    0.49
     campe
    0.47
     banker
    0.46
     energético
    0.46
     financiero
    0.46
     rentable
    0.46
     financiera
    0.46
    Activations Density 0.000%

    No Known Activations