© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130808
    Prev
    Next
    INDEX
    Explanations

    headlines or list titles

    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
    ે
    0.76
    ătoare
    0.74
    ة
    0.74
    он
    0.71
    માં
    0.71
    い
    0.70
    وان
    0.66
    ή
    0.65
    цију
    0.65
    ين
    0.64
    POSITIVE LOGITS
    8
    1.05
    v
    1.01
    7
    1.01
    ll
    0.90
    9
    0.87
    el
    0.85
    t
    0.83
    da
    0.82
    ta
    0.82
    ↵
    0.82
    Activations Density 0.001%

    No Known Activations