© 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. 5898
    Prev
    Next
    INDEX
    Explanations

    aj followed by zen, iac, or io

    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
    ⣀
    0.41
     Highlander
    0.39
    ారణ
    0.39
     Hit
    0.38
     Mora
    0.38
    Sov
    0.38
     Horner
    0.37
     hit
    0.37
    Hammer
    0.37
     curd
    0.36
    POSITIVE LOGITS
     AGRICULTURE
    0.40
    interface
    0.39
    APT
    0.39
    communications
    0.39
     ಅರ್ಥ
    0.38
    綁
    0.38
    接口
    0.37
    datast
    0.37
    get
    0.37
    arts
    0.36
    Activations Density 0.002%

    No Known Activations