© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121863
    Prev
    Next
    INDEX
    Explanations

    freezer, free, ports

    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
    ↵
    0.89
     do
    0.81
    的核心
    0.75
     don
    0.75
    of
    0.72
     הד
    0.70
     który
    0.70
    <bos>
    0.66
    િસ
    0.66
     précise
    0.64
    POSITIVE LOGITS
    ل
    1.04
    r
    0.97
    l
    0.94
    c
    0.93
    л
    0.92
    لک
    0.84
    ル
    0.82
    textColor
    0.78
    ल
    0.77
    ல்
    0.76
    Activations Density 0.001%

    No Known Activations