© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42896
    Prev
    Next
    INDEX
    Explanations

    price and value

    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_22_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
     primaire
    0.44
    riend
    0.43
    rosophila
    0.41
    ead
    0.41
    iew
    0.40
    背
    0.40
    DataReader
    0.40
    amos
    0.39
    arian
    0.39
    gyz
    0.39
    POSITIVE LOGITS
     वि
    0.43
    dı
    0.41
     destined
    0.41
     normalmente
    0.40
     belie
    0.38
     সম্প
    0.38
    ),$
    0.38
     массив
    0.37
     grazed
    0.37
     চি
    0.37
    Activations Density 0.018%

    No Known Activations