© 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-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200872
    Prev
    Next
    INDEX
    Explanations

    concrete, pavement, and lots

    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_12_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
     adhé
    0.28
    mitglied
    0.28
     sustain
    0.26
    อยู่ใน
    0.25
     masy
    0.25
     pall
    0.25
    절
    0.25
     febru
    0.24
     Vou
    0.24
    สา
    0.24
    POSITIVE LOGITS
    *
    0.29
    *\*
    0.23
     elaborado
    0.23
     призначення
    0.23
    *;
    0.23
    is
    0.22
    Kem
    0.22
     Kwiatkowski
    0.22
    '
    0.22
    izace
    0.22
    Activations Density 0.002%

    No Known Activations