© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 197019
    Prev
    Next
    INDEX
    Explanations

    mentioning specific topics

    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
    ണിത്
    0.42
    τούν
    0.41
     Это
    0.38
    ஆம்
    0.38
    洳
    0.38
     marginRight
    0.37
     ہے۔
    0.37
    沚
    0.37
    Это
    0.37
     ریاست
    0.36
    POSITIVE LOGITS
    cha
    0.40
     focusing
    0.35
    atório
    0.34
    odo
    0.34
     focus
    0.33
    OCO
    0.33
    ophane
    0.33
    apos
    0.32
     privilege
    0.32
    klad
    0.31
    Activations Density 0.023%

    No Known Activations