© 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. 201353
    Prev
    Next
    INDEX
    Explanations

    codecademy

    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
    кован
    0.27
     MILLER
    0.26
    율
    0.25
     negar
    0.25
     rechaz
    0.25
     vencedor
    0.25
     бо
    0.24
     regimes
    0.24
     табли
    0.24
     allocated
    0.24
    POSITIVE LOGITS
    æt
    0.28
    ://
    0.28
    P
    0.26
    Color
    0.25
    V
    0.25
    With
    0.24
    There
    0.24
    4
    0.24
    kommen
    0.23
    OL
    0.23
    Activations Density 0.002%

    No Known Activations