© 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. 120888
    Prev
    Next
    INDEX
    Explanations

    what are

    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
    }^{+}=
    0.37
    ຜະລິດຕ
    0.35
     দিল্লিতে
    0.35
    含む
    0.32
    䘚
    0.32
    ল্যান্ড
    0.32
     मि
    0.31
    㫙
    0.31
    弹性
    0.30
    ANDS
    0.30
    POSITIVE LOGITS
    œuvre
    0.35
     sag
    0.34
     vam
    0.34
     "|"
    0.33
    Ich
    0.33
     nen
    0.33
     noen
    0.33
     fortsatt
    0.33
    ían
    0.32
     wild
    0.32
    Activations Density 0.007%

    No Known Activations