© 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
    2. Gemma-3-27B-IT
    3. 59-GEMMASCOPE-2-TRANSCODER-262K
    4. 60359
    Prev
    Next
    INDEX
    Explanations

    refusal of harmful content

    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_59_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
    	
    0.54
    \[
    0.48
    <\/
    0.47
    The
    0.46
    ***
    0.45
    <0x0F>
    0.44
    </
    0.42
    �
    0.42
    <0x1C>
    0.42
    <0x19>
    0.41
    POSITIVE LOGITS
     offence
    0.44
    -
    0.44
     celebs
    0.43
     mors
    0.42
     offense
    0.41
     offences
    0.41
     were
    0.41
     offenses
    0.41
     regimes
    0.41
    categoryId
    0.40
    Activations Density 0.011%

    No Known Activations