© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7073
    Prev
    Next
    INDEX
    Explanations

    resource library links

    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_39_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
     प्राइमरी
    0.46
     motives
    0.40
     PRIMARY
    0.39
     primary
    0.38
     motive
    0.38
    黜
    0.38
    洞
    0.37
    γή
    0.37
     contrato
    0.37
     worshipped
    0.37
    POSITIVE LOGITS
     strands
    0.40
    student
    0.40
     Academic
    0.39
     strand
    0.38
     student
    0.37
     Exempl
    0.37
     parap
    0.37
     Directions
    0.37
     Gu
    0.36
    學生
    0.36
    Activations Density 0.020%

    No Known Activations