© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50812
    Prev
    Next
    INDEX
    Explanations

    physical states/changes

    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_55_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
    wey
    0.37
     деб
    0.37
    amanya
    0.37
    缨
    0.37
    माला
    0.36
    Experience
    0.36
    流行
    0.36
    ξι
    0.36
    丈
    0.36
    Sends
    0.35
    POSITIVE LOGITS
     obstruct
    0.46
     bruised
    0.46
     eroded
    0.43
     Inj
    0.39
     heal
    0.39
     erode
    0.39
    crum
    0.39
     stagnant
    0.39
     injured
    0.38
     regress
    0.38
    Activations Density 0.008%

    No Known Activations