© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213524
    Prev
    Next
    INDEX
    Explanations

    Niche Down

    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_5_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
    u
    1.20
    at
    0.84
    ti
    0.73
    ta
    0.73
    uot
    0.68
    ти
    0.64
    n
    0.64
    t
    0.64
    uk
    0.62
    uwa
    0.61
    POSITIVE LOGITS
     في
    0.80
     in
    0.71
    _
    0.71
     an
    0.67
     ي
    0.61
     وك
    0.60
     σε
    0.59
     do
    0.59
    。
    0.58
    };
    0.58
    Activations Density 0.002%

    No Known Activations