© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44046
    Prev
    Next
    INDEX
    Explanations

    freshen

    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_3_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
    l
    0.97
    ss
    0.87
    sc
    0.84
    ls
    0.84
    n
    0.84
    sen
    0.80
    k
    0.78
    ri
    0.77
    0.75
    ran
    0.75
    POSITIVE LOGITS
    ية
    0.91
    ৬
    0.87
    ৯
    0.81
    ła
    0.75
    ین
    0.75
    ]);
    0.73
    śl
    0.71
    ]."
    0.70
     перегово
    0.70
     conciertos
    0.70
    Activations Density 0.000%

    No Known Activations