© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49298
    Prev
    Next
    INDEX
    Explanations

    forming or connection

    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
    separated
    0.48
    Unlocked
    0.40
     separated
    0.39
    separ
    0.38
    综艺
    0.37
    fueled
    0.36
    obtained
    0.36
    失
    0.36
    ()!=
    0.36
     geschrieben
    0.36
    POSITIVE LOGITS
     ann
    0.40
     maken
    0.39
     neighboring
    0.39
     contacter
    0.38
    වැ
    0.38
     suiv
    0.37
     منظور
    0.37
     Forming
    0.37
     forming
    0.36
     panc
    0.36
    Activations Density 0.027%

    No Known Activations