© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37183
    Prev
    Next
    INDEX
    Explanations

    location names and associated activities

    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_3_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
    場合に
    0.65
     rework
    0.55
    á
    0.55
     modification
    0.55
     groundbreaking
    0.55
    ➜
    0.55
     trouver
    0.54
     ३
    0.54
     armament
    0.53
     quá
    0.53
    POSITIVE LOGITS
    ان
    0.88
    r
    0.84
    _
    0.83
    ر
    0.82
    an
    0.77
    1
    0.77
    he
    0.74
    0
    0.72
    𝘱
    0.72
    sh
    0.71
    Activations Density 0.000%

    No Known Activations