© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15388
    Prev
    Next
    INDEX
    Explanations

    Icelandic words and Swedish words

    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_34_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
     c
    0.55
     neu
    0.50
    ̃
    0.47
     pom
    0.44
    uil
    0.44
    ries
    0.42
     chem
    0.41
     C
    0.41
     SARS
    0.41
    ies
    0.40
    POSITIVE LOGITS
    På
    0.67
     produkter
    0.64
    Så
    0.63
     Når
    0.60
     samtidig
    0.60
    Hvis
    0.57
     påver
    0.57
     får
    0.55
     vanlig
    0.55
     år
    0.54
    Activations Density 0.001%

    No Known Activations