© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22135
    Prev
    Next
    INDEX
    Explanations

    `

    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_56_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
    N
    0.66
    Ｎ
    0.65
    𝑁
    0.65
     एन
    0.63
    एन
    0.61
    এন
    0.59
    Nz
    0.58
    Nx
    0.54
     Nx
    0.54
    Np
    0.52
    POSITIVE LOGITS
     differing
    0.39
     loudly
    0.38
     DOF
    0.36
     unsettled
    0.36
    Interestingly
    0.36
     HIS
    0.35
    กี
    0.35
    érin
    0.35
     Mist
    0.35
     interestingly
    0.35
    Activations Density 0.011%

    No Known Activations