© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 212276
    Prev
    Next
    INDEX
    Explanations

    item received damaged or not

    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_19_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
    戻
    0.41
    LER
    0.40
    除
    0.40
     सक्रिय
    0.39
    ⏎
    0.39
    racellular
    0.38
     оса
    0.37
    に戻
    0.37
     除
    0.37
    㳚
    0.37
    POSITIVE LOGITS
     doce
    0.52
     manquer
    0.51
     prazer
    0.48
     perpetuity
    0.48
     reproduction
    0.46
     महिले
    0.45
     liberties
    0.45
     provoke
    0.45
     cloves
    0.44
     anore
    0.44
    Activations Density 0.002%

    No Known Activations