© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 240451
    Prev
    Next
    INDEX
    Explanations

    tower and towers

    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_25_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
     คลิป
    0.38
    örk
    0.38
    🖇
    0.37
     家具
    0.37
     कंडक्टर
    0.37
    Showing
    0.37
     行
    0.37
    КА
    0.37
    不开
    0.37
    ครอง
    0.37
    POSITIVE LOGITS
     sopra
    0.43
     Thought
    0.41
    emy
    0.39
     neph
    0.38
     Instru
    0.37
     kes
    0.37
    EMY
    0.37
     ip
    0.37
     '".$
    0.37
     trasmissione
    0.36
    Activations Density 0.001%

    No Known Activations