© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121304
    Prev
    Next
    INDEX
    Explanations

    also follows with additional info

    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_27_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
     Likewise
    0.55
     likewise
    0.48
    Likewise
    0.41
    >>
    0.40
     respectivement
    0.40
    ведите
    0.38
    стите
    0.37
     hasty
    0.37
    idem
    0.36
     ايضا
    0.35
    POSITIVE LOGITS
    缸
    0.40
     اجازه
    0.39
     cytochrome
    0.39
     menino
    0.38
     ELISA
    0.38
     Opa
    0.38
     ácidos
    0.38
     لما
    0.37
     accommodates
    0.37
    钞
    0.37
    Activations Density 0.001%

    No Known Activations