© 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. 8058
    Prev
    Next
    INDEX
    Explanations

    withholding or withdrawal

    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
    م
    2.86
     faptul
    2.76
     começ
    2.76
    मित
    2.54
     साथ
    2.53
    म
    2.52
    স্ট
    2.45
    \}
    2.44
    মল
    2.39
    iquement
    2.38
    POSITIVE LOGITS
    માં
    2.96
    ្ស
    2.71
    ת
    2.68
     commerciali
    2.67
     rigidbody
    2.42
    baptism
    2.42
     demeanor
    2.39
    ಡಿದ
    2.36
    hah
    2.33
    twitch
    2.33
    Activations Density 0.016%

    No Known Activations