© 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. 194251
    Prev
    Next
    INDEX
    Explanations

    writing paragraphs

    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
     "
    0.40
    到
    0.40
     Un
    0.39
     marsh
    0.39
     danger
    0.39
     Partial
    0.38
     un
    0.37
     --
    0.36
    search
    0.36
     benefit
    0.36
    POSITIVE LOGITS
    ごとに
    0.44
     চিৎ
    0.41
    魧
    0.41
     করিয়৷
    0.41
     அரங்க
    0.41
    তত্ব
    0.40
    ሎ
    0.40
     PURCH
    0.40
    棸
    0.40
    obtenir
    0.40
    Activations Density 0.006%

    No Known Activations