© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21624
    Prev
    Next
    INDEX
    Explanations

    Baltic/Finnic languages

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    她
    0.47
     ',');
    0.44
     него
    0.43
     нее
    0.42
     нього
    0.42
     Allo
    0.38
    she
    0.38
     вона
    0.37
    DriverManager
    0.37
    iquen
    0.36
    POSITIVE LOGITS
    ää
    0.91
     ț
    0.62
    äär
    0.58
     ä
    0.52
     Ä
    0.46
     ё
    0.45
    äänt
    0.44
     AAC
    0.43
    Aaron
    0.42
     ul
    0.42
    Activations Density 0.001%

    No Known Activations