© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258397
    Prev
    Next
    INDEX
    Explanations

    movement towards a goal

    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_22_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
     arkadaşlar
    0.41
     médi
    0.41
     medici
    0.39
     médic
    0.38
    醫
    0.38
     diploma
    0.38
    »
    0.38
     sports
    0.38
     blí
    0.37
     famosa
    0.37
    POSITIVE LOGITS
     TextFormField
    0.43
    쩝
    0.42
     Fraud
    0.41
    igon
    0.41
    ogenies
    0.40
    Fraud
    0.39
    ডস
    0.39
    Seq
    0.38
     ব্যাটসম্যান
    0.38
    ็ด
    0.37
    Activations Density 0.000%

    No Known Activations