© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7114
    Prev
    Next
    INDEX
    Explanations

    `app.run(debug=True)`

    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_39_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
    adrat
    0.40
     assessments
    0.39
    म्पियन
    0.39
    विष्ट
    0.38
    ើន
    0.38
    astricht
    0.38
     furiously
    0.38
    }^{+}+
    0.38
    分的
    0.37
     fates
    0.37
    POSITIVE LOGITS
     rot
    0.41
     бой
    0.36
    Section
    0.36
    Dining
    0.36
    SECTION
    0.35
    dining
    0.35
    Bucket
    0.35
     protr
    0.34
     Projection
    0.34
    THREAD
    0.34
    Activations Density 0.011%

    No Known Activations