© 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. 211499
    Prev
    Next
    INDEX
    Explanations

    alternative hypothesis

    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
     </
    0.45
     Discharge
    0.42
    Transfer
    0.42
     Bail
    0.40
     },
    0.40
     '</
    0.40
    否
    0.40
    Frequency
    0.39
     discharged
    0.39
    indagi
    0.39
    POSITIVE LOGITS
     consid
    0.48
     नियोक्ता
    0.47
     Oktober
    0.47
     মধ্য
    0.45
     educators
    0.44
     நகரம்
    0.44
    ੱਖ
    0.44
    ཧ
    0.44
     pä
    0.44
     powerhouse
    0.44
    Activations Density 0.001%

    No Known Activations