© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 142249
    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_46_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
    क्रोश
    0.45
     Reservation
    0.42
    闊
    0.40
    vb
    0.39
    Yea
    0.38
     Dumb
    0.37
     VB
    0.37
     vb
    0.36
     நாள்
    0.36
    tb
    0.36
    POSITIVE LOGITS
    astern
    0.38
    ammens
    0.38
    ]`
    0.37
    ্ঠ
    0.37
    -}$
    0.35
     গ্যা
    0.35
    —.
    0.35
    itäten
    0.34
    gaz
    0.34
    яс
    0.34
    Activations Density 0.001%

    No Known Activations