© 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-3-27B-IT
    3. 39-GEMMASCOPE-2-TRANSCODER-262K
    4. 4302
    Prev
    Next
    INDEX
    Explanations

    elements and their symbols

    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_39_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
    Mineral
    0.25
     минера
    0.23
     mineralization
    0.22
    𒊏
    0.22
     minerales
    0.21
     Mineral
    0.21
     MINERAL
    0.20
    礦
    0.20
    mineral
    0.20
    矿
    0.20
    POSITIVE LOGITS
     P
    0.20
     authentic
    0.19
    sur
    0.18
    j
    0.18
    authentic
    0.18
    ty
    0.17
    kl
    0.17
     Kl
    0.17
    P
    0.16
     Cen
    0.16
    Activations Density 0.048%

    No Known Activations