© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 197085
    Prev
    Next
    INDEX
    Explanations

    desert landscapes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    МИ
    0.42
    নায়
    0.39
     Berge
    0.38
    钢
    0.36
    ческую
    0.36
    철
    0.36
    味料
    0.35
    سته
    0.35
    磋
    0.35
    чески
    0.35
    POSITIVE LOGITS
    ੍ਹ
    0.46
     Manifest
    0.45
     manifestations
    0.43
     manifests
    0.42
     মৃত
    0.41
     Gb
    0.41
    stimulated
    0.40
     Net
    0.40
     macro
    0.39
     manifestaciones
    0.38
    Activations Density 0.001%

    No Known Activations