© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132504
    Prev
    Next
    INDEX
    Explanations

    docstrings

    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_6_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
    К
    1.54
    ي
    1.44
    י
    1.26
    i
    1.24
    '
    1.24
     at
    1.23
    ]
    1.19
    사
    1.13
    e
    1.11
    Т
    1.09
    POSITIVE LOGITS
    ala
    1.09
    ina
    1.09
    än
    1.00
    0.99
    eti
    0.93
    elijkheid
    0.92
    ali
    0.88
    ete
    0.88
    nia
    0.88
    lar
    0.87
    Activations Density 0.002%

    No Known Activations