© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136521
    Prev
    Next
    INDEX
    Explanations

    that best describes the neuron's behavior based on the provided lists is:**feature**, **in**, **algorithmic**, **playlists**

    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_12_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
    º
    0.55
    ¹.
    0.51
    హ
    0.49
     grayish
    0.49
    錶
    0.49
    °.
    0.48
    ਹਾ
    0.48
     वेबसाइट
    0.48
    ophyll
    0.48
     AFTER
    0.48
    POSITIVE LOGITS
    t
    0.64
     patrols
    0.59
     cameras
    0.58
    たる
    0.57
     Parkway
    0.55
    0.55
     camera
    0.53
     카메라
    0.53
     incarcer
    0.52
     roam
    0.52
    Activations Density 0.001%

    No Known Activations