© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 105171
    Prev
    Next
    INDEX
    Explanations

    say dangerous

    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_44_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
     уста
    0.44
     nCenters
    0.42
     NED
    0.40
     N
    0.40
    وک
    0.39
    ᴺ
    0.38
     NVARCHAR
    0.38
    SC
    0.38
    agons
    0.38
    N
    0.38
    POSITIVE LOGITS
     آبی
    0.40
     pure
    0.39
    ematic
    0.38
     Europese
    0.37
     bepa
    0.37
    ypter
    0.37
     Đối
    0.35
     Богу
    0.35
     leichte
    0.35
    pure
    0.34
    Activations Density 0.016%

    No Known Activations