© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211654
    Prev
    Next
    INDEX
    Explanations

    safety/ethical boundaries

    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_5_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
    ிறது
    1.38
     seva
    1.16
    ેલી
    1.16
    oled
    1.12
    не
    1.07
    ે
    1.06
    போது
    1.02
    ו
    1.02
    ність
    1.01
     examin
    1.01
    POSITIVE LOGITS
    ET
    1.31
    ICK
    1.30
    Az
    1.23
    Ak
    1.20
     })
    1.20
    </code>
    1.17
    with
    1.15
    '])
    1.15
    Ich
    1.15
    Ik
    1.15
    Activations Density 0.004%

    No Known Activations