© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 99662
    Prev
    Next
    INDEX
    Explanations

    problem asks you to determine

    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_16_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
    คอง
    0.54
     ໃນ
    0.49
     ਕੋ
    0.47
    ]$;
    0.47
    skiy
    0.46
    seit
    0.45
     creek
    0.45
     হাকি
    0.44
     цей
    0.43
     ხელ
    0.43
    POSITIVE LOGITS
    inna
    0.45
     reproducción
    0.44
    क्व
    0.43
    Utc
    0.41
     Tourism
    0.41
    첩
    0.40
    Advertise
    0.40
     specified
    0.40
     stoichi
    0.40
     heterogeneity
    0.39
    Activations Density 0.000%

    No Known Activations