© 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. 194924
    Prev
    Next
    INDEX
    Explanations

    episode count

    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
     Cot
    0.37
     azt
    0.37
     tê
    0.36
     recouvre
    0.35
    苛
    0.35
    扱う
    0.35
     বাসস্থান
    0.35
    葱
    0.35
     ober
    0.35
     Porte
    0.34
    POSITIVE LOGITS
     episod
    0.47
     consistently
    0.44
    glEnd
    0.42
     provoked
    0.38
    Episode
    0.37
     provoke
    0.37
    requently
    0.36
    ιουργ
    0.36
    Fixed
    0.36
    PLF
    0.36
    Activations Density 0.001%

    No Known Activations