© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 8611
    Prev
    Next
    INDEX
    Explanations

    helicopter parenting, helicobacter, chopper

    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
     humana
    2.74
     actes
    2.56
    holders
    2.56
    位的
    2.47
    ње
    2.45
     celebra
    2.42
     দেয়
    2.40
    儡
    2.37
    ದೇ
    2.32
     hati
    2.32
    POSITIVE LOGITS
    𝗻
    3.02
    おり
    2.76
    জ্ঞান
    2.72
    难题
    2.67
    品种
    2.67
    as
    2.66
    ي
    2.65
    ്
    2.54
    UAGE
    2.53
    શ્મી
    2.51
    Activations Density 0.012%

    No Known Activations