© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205765
    Prev
    Next
    INDEX
    Explanations

    names

    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_56_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
    ът
    0.36
    manager
    0.35
     मैनेजर
    0.35
    തിന്റെ
    0.35
    getMove
    0.35
    estern
    0.34
    📓
    0.33
    mathbf
    0.32
    ፃ
    0.32
    慚
    0.32
    POSITIVE LOGITS
    ''''
    0.39
     theres
    0.38
     whats
    0.38
     Luego
    0.37
    Thats
    0.36
    질
    0.36
    <0xD5>
    0.36
    
    0.35
     Thats
    0.35
    ''
    0.35
    Activations Density 0.000%

    No Known Activations