© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81656
    Prev
    Next
    INDEX
    Explanations

    bring the troops home / charges

    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_0_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
    1
    2.19
    3
    2.13
    ש
    1.75
    9
    1.65
    8
    1.65
    6
    1.61
    ین
    1.53
    ید
    1.53
    ים
    1.48
    ו
    1.45
    POSITIVE LOGITS
    c
    1.73
    g
    1.62
    ،
    1.62
    ，
    1.55
    、
    1.35
    p
    1.27
    ০১
    1.23
    ０
    1.22
    gnet
    1.18
    k
    1.16
    Activations Density 0.000%

    No Known Activations