© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159887
    Prev
    Next
    INDEX
    Explanations

    cannot perform action

    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_2_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
    ي
    1.84
    ма
    1.47
    ために
    1.34
    いますが
    1.30
    ка
    1.30
    й
    1.30
    ع
    1.30
    Untuk
    1.24
    ون
    1.22
    മ
    1.18
    POSITIVE LOGITS
     for
    1.08
    ının
    1.08
     mondo
    1.02
    0.99
     The
    0.95
    েরি
    0.95
     lifeboat
    0.94
     on
    0.93
    
    0.92
    ელ
    0.86
    Activations Density 0.000%

    No Known Activations