© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 2405
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    ر
    3.65
    er
    2.87
    ان
    2.82
    การ
    2.76
    ()=>{
    2.76
    e
    2.73
    voorbeeld
    2.61
     चलते
    2.55
    ../
    2.48
    ことになる
    2.44
    POSITIVE LOGITS
    ς
    3.08
     rationale
    2.84
    ரிய
    2.79
    ի
    2.72
    dong
    2.61
    dicke
    2.60
    dob
    2.58
    т
    2.55
     Installations
    2.55
    Nobody
    2.53
    Activations Density 0.024%

    No Known Activations