© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62026
    Prev
    Next
    INDEX
    Explanations

    hobbies and interests

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    it
    0.44
    ln
    0.41
     ar
    0.41
     :
    0.39
    its
    0.38
    Illust
    0.37
     qualifies
    0.37
    Anal
    0.36
     equates
    0.36
     acknowledges
    0.36
    POSITIVE LOGITS
     All
    0.59
     Bad
    0.58
     Art
    0.54
     From
    0.53
     Br
    0.50
     Б
    0.49
     Any
    0.49
     Been
    0.48
     Be
    0.48
     At
    0.47
    Activations Density 0.005%

    No Known Activations