© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175394
    Prev
    Next
    INDEX
    Explanations

    user, buyer, customer, student, learner

    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_24_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
    кте
    0.45
    瑪
    0.43
     امریک
    0.41
    アメリカ
    0.41
    氿
    0.41
     있는데요
    0.40
    Lower
    0.40
    私たちの
    0.40
    ﹝
    0.40
     électron
    0.40
    POSITIVE LOGITS
     সমগ্র
    0.46
     east
    0.41
     cloud
    0.39
     clouds
    0.38
     eastern
    0.38
     eastward
    0.38
     goes
    0.37
     fenced
    0.37
     terraces
    0.37
     far
    0.36
    Activations Density 0.005%

    No Known Activations