© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 89245
    Prev
    Next
    INDEX
    Explanations

    IBM and related tech companies

    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_18_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
    லாத
    0.54
     Gian
    0.48
    a
    0.47
    Gian
    0.45
     ACB
    0.44
     AP
    0.43
     причем
    0.43
     locally
    0.43
     Muchos
    0.43
     useful
    0.42
    POSITIVE LOGITS
    OrderFlight
    0.47
    𝗷
    0.45
    ENDER
    0.43
    OGLE
    0.43
    ปล
    0.42
     meninas
    0.42
    朋友們
    0.42
    yskland
    0.42
    េស
    0.41
     secolo
    0.41
    Activations Density 0.001%

    No Known Activations