© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120475
    Prev
    Next
    INDEX
    Explanations

    abstract section

    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_27_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
    陽
    0.35
    +)
    0.35
    old
    0.33
     давно
    0.33
     entr
    0.33
     combined
    0.33
     midst
    0.32
     “…
    0.32
    เข้าไป
    0.32
    중
    0.32
    POSITIVE LOGITS
    喜欢的
    0.39
     ardından
    0.38
    ανο
    0.38
    哑
    0.38
    çou
    0.37
    备案
    0.37
    ্সর
    0.37
     رہتا
    0.36
    形象
    0.36
     taxed
    0.36
    Activations Density 0.000%

    No Known Activations