© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50482
    Prev
    Next
    INDEX
    Explanations

    certain ethical

    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_30_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
    avaju
    0.40
    corpus
    0.39
     வடிக
    0.38
     सलाद
    0.38
    rawdę
    0.37
    ecommerce
    0.36
    —.
    0.36
    __."
    0.36
    owntown
    0.35
    POSITIVE LOGITS
     stronger
    0.44
     zaidi
    0.38
    ׂ
    0.38
     HS
    0.37
     сильнее
    0.35
    Endpoints
    0.34
     posizione
    0.34
    ிலும்
    0.33
     villes
    0.33
    ждый
    0.33
    Activations Density 0.013%

    No Known Activations