© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46314
    Prev
    Next
    INDEX
    Explanations

    alphanumeric and text processing

    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_13_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
     жела
    0.44
     desiring
    0.41
    ί
    0.38
     Ă
    0.38
    りたい
    0.37
    ēj
    0.37
    ěk
    0.37
     úgy
    0.36
     obtains
    0.36
    żyt
    0.36
    POSITIVE LOGITS
    שה
    0.37
    ضمن
    0.36
    جز
    0.34
    ت
    0.34
    和
    0.34
    Running
    0.33
    <b>
    0.33
    Thumbnail
    0.33
    正面
    0.32
    Lighting
    0.32
    Activations Density 0.049%

    No Known Activations