© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58885
    Prev
    Next
    INDEX
    Explanations

    network security, components, usage

    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_2_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
    ח
    1.45
    ك
    1.41
    ן
    1.38
    م
    1.34
    на
    1.28
    ка
    1.24
    મ
    1.24
    ب
    1.22
    ম
    1.20
    ق
    1.20
    POSITIVE LOGITS
    '
    1.93
    ’
    1.33
    。
    1.31
    to
    1.18
    '।
    1.15
    ্ড
    1.14
    p
    1.10
    st
    0.97
    iť
    0.97
    ti
    0.97
    Activations Density 0.014%

    No Known Activations