© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51252
    Prev
    Next
    INDEX
    Explanations

    secondary school

    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_31_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
     পুরা
    0.47
    स्टोन
    0.38
    četně
    0.36
    不要
    0.35
    ᑉ
    0.35
    contenedor
    0.35
     exponent
    0.34
     drewn
    0.34
    ogad
    0.34
    晹
    0.33
    POSITIVE LOGITS
     academic
    0.43
     Campus
    0.41
     Academic
    0.40
    abbit
    0.38
    academic
    0.38
     Aces
    0.38
     Ach
    0.37
    Academic
    0.37
     Faculté
    0.36
     શિક્ષણ
    0.35
    Activations Density 0.001%

    No Known Activations