© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 208197
    Prev
    Next
    INDEX
    Explanations

    list context keywords

    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_10_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
    8
    0.66
    2
    0.63
    。
    0.62
    4
    0.62
    DM
    0.60
    م
    0.58
    7
    0.58
    UM
    0.57
    else
    0.57
    5
    0.57
    POSITIVE LOGITS
     errorMessage
    0.70
    s
    0.69
     VoIP
    0.67
     wartość
    0.67
     potre
    0.66
    sbParams
    0.66
     nevoia
    0.66
     USER
    0.64
     piattaforma
    0.64
     physiotherapy
    0.64
    Activations Density 0.000%

    No Known Activations