© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170709
    Prev
    Next
    INDEX
    Explanations

    it

    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
     it
    1.63
    มัน
    1.43
    它
    1.41
    ມັນ
    1.16
     它
    1.15
    它可以
    1.12
     nó
    1.09
     มัน
    1.04
    它是
    0.99
     এটি
    0.98
    POSITIVE LOGITS
    その
    0.44
    osus
    0.38
     εκεί
    0.38
    isinin
    0.38
    posição
    0.36
     istiyorum
    0.36
    瀨
    0.36
    otos
    0.35
    Have
    0.35
    ="))
    0.35
    Activations Density 0.003%

    No Known Activations