© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203184
    Prev
    Next
    INDEX
    Explanations

    recharge meaning or use

    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
    3
    1.20
    at
    1.15
    4
    1.10
    2
    1.09
    is
    1.02
    l
    0.96
    live
    0.92
    a
    0.92
    ре
    0.91
    after
    0.91
    POSITIVE LOGITS
    <0x80>
    0.96
    t
    0.86
     TestAvg
    0.86
    вані
    0.83
     œufs
    0.81
    梫
    0.80
     ambiental
    0.78
    ꗥ
    0.78
     independ
    0.78
     rése
    0.78
    Activations Density 0.001%

    No Known Activations