© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 41-GEMMASCOPE-2-TRANSCODER-262K
    4. 63316
    Prev
    Next
    INDEX
    Explanations

    velvet fabric

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_41_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
     ایکسپ
    0.38
    萫
    0.38
    ={<
    0.37
    脅
    0.37
     Lilly
    0.36
    胤
    0.36
     threatened
    0.36
    Hector
    0.36
     সঞ্জীবনী
    0.36
    𒅆
    0.36
    POSITIVE LOGITS
     velvet
    1.85
     Velvet
    1.66
     vel
    1.55
     velv
    1.44
    Vel
    1.43
     VEL
    1.43
     velvety
    1.41
     Vel
    1.33
    vel
    1.27
    VEL
    1.21
    Activations Density 0.011%

    No Known Activations