© 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
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6177
    Prev
    Next
    INDEX
    Explanations

    destructive

    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
    nancy
    2.68
    場合
    2.53
     grated
    2.50
    ℝ
    2.34
    𝐳
    2.33
     restrained
    2.32
     ovip
    2.31
     steeple
    2.29
     purifying
    2.27
    ein
    2.26
    POSITIVE LOGITS
     komme
    2.38
     efficiencies
    2.33
    л
    2.25
    டோ
    2.10
    raft
    2.08
    ى
    2.02
    בים
    1.99
     rapports
    1.99
    楂
    1.95
     alcanz
    1.93
    Activations Density 0.033%

    No Known Activations