© 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
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3133
    Prev
    Next
    INDEX
    Explanations

    the followed by specific nouns

    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_5_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
     crustaceans
    0.44
     urination
    0.40
    ">)</
    0.39
     waged
    0.39
    ّد
    0.38
    لر
    0.38
    десят
    0.38
    oretically
    0.37
    EndInit
    0.37
     હાલ
    0.37
    POSITIVE LOGITS
    р
    0.35
    lii
    0.33
    Natal
    0.33
    me
    0.33
    hatan
    0.33
    pt
    0.32
    ba
    0.32
    pst
    0.32
    它
    0.32
    m
    0.32
    Activations Density 0.033%

    No Known Activations