© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 177224
    Prev
    Next
    INDEX
    Explanations

    kill

    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_50_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
    LEXPORT
    0.44
    ho
    0.38
    icom
    0.38
    しの
    0.36
     اللي
    0.36
    ApiModel
    0.36
    拎
    0.36
    ilim
    0.35
    Anast
    0.34
    сным
    0.34
    POSITIVE LOGITS
     prés
    0.42
     Copern
    0.40
     Frenchman
    0.39
     Alsace
    0.39
    诀
    0.39
     Pres
    0.38
     Cop
    0.38
    ចុ
    0.38
     Siemens
    0.37
    теро
    0.37
    Activations Density 0.001%

    No Known Activations