© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 897
    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
    ه
    2.47
    
    2.41
    े
    2.28
    가
    2.26
    tors
    2.20
    at
    2.16
    ρ
    2.16
     Ambedkar
    2.10
    ли
    2.02
    সোমবার
    2.02
    POSITIVE LOGITS
    師
    1.96
    <0x80>
    1.79
    ской
    1.71
    setColor
    1.69
    ắn
    1.67
     poważ
    1.66
     dalších
    1.65
    ță
    1.63
    ے
    1.63
     splendid
    1.63
    Activations Density 0.007%

    No Known Activations