© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5561
    Prev
    Next
    INDEX
    Explanations

    verbs related to facilitating, permitting or enabling

    oai_token-act-pair · gemini-2.0-flash

    prepositions indicating allowance or purpose

    np_token-act-pair-logits · gpt-4o-mini

    allow

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oredCriteria
    -0.72
    aarrggbb
    -0.71
    endphp
    -0.69
     '\\;'
    -0.67
    featureID
    -0.67
    enderror
    -0.65
     Administrativna
    -0.63
    ::_('
    -0.63
    IsPostBack
    -0.60
    mobileqq
    -0.59
    POSITIVE LOGITS
     for
    2.86
    for
    2.02
     для
    1.70
     für
    1.59
     voor
    1.58
     untuk
    1.52
     FOR
    1.42
     pentru
    1.42
     برای
    1.41
     για
    1.38
    Activations Density 2.726%

    No Known Activations