© 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. 120759
    Prev
    Next
    INDEX
    Explanations

    That's kind of

    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
     collapsible
    0.40
     milk
    0.39
     cooling
    0.37
     steaming
    0.36
     nondestructive
    0.36
     offsetting
    0.36
    《
    0.36
     ultrasound
    0.36
     Byrd
    0.36
     Markham
    0.35
    POSITIVE LOGITS
    licted
    0.34
    㫧
    0.34
    שו
    0.33
    Describes
    0.33
    Victoria
    0.33
    ării
    0.32
    Nic
    0.32
    ias
    0.32
    ouer
    0.32
    ש
    0.31
    Activations Density 0.007%

    No Known Activations