© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8416
    Prev
    Next
    INDEX
    Explanations

    crack / cracking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     불구하고
    2.77
    żeń
    2.66
    ্লাহ
    2.57
    zeug
    2.51
    ᴺ
    2.48
    enie
    2.45
    ش
    2.44
    af
    2.44
     hemicontinuous
    2.43
     akin
    2.43
    POSITIVE LOGITS
    ট
    2.91
    今まで
    2.89
    p
    2.79
    Hiện
    2.73
    दार
    2.62
    vice
    2.61
    これまで
    2.60
    イ
    2.53
    р
    2.52
    今
    2.50
    Activations Density 0.031%

    No Known Activations