© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59153
    Prev
    Next
    INDEX
    Explanations

    you / seeing you

    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_11_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
    x
    0.34
    matter
    0.32
    EndInit
    0.32
    i
    0.30
    cdot
    0.30
     가장
    0.30
     것을
    0.30
    stantially
    0.30
    かもしれませんが
    0.30
     さらに
    0.29
    POSITIVE LOGITS
    。
    0.29
     Kelas
    0.28
     nieuws
    0.27
    <0x98>
    0.26
    น
    0.26
     aktiv
    0.26
    ला
    0.26
     kelas
    0.25
     OTP
    0.25
     PIR
    0.25
    Activations Density 0.026%

    No Known Activations