© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4191
    Prev
    Next
    INDEX
    Explanations

    the word "any" either on its own or close to words "the", "our", or "their"

    oai_token-act-pair · gemini-2.0-flash

    types and categories

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

    any

    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
    AndEndTag
    -0.93
     '\\;'
    -0.85
    fjspx
    -0.75
     AttributeSet
    -0.73
    BeginContext
    -0.72
     handleMessage
    -0.70
     GenerationType
    -0.69
    featureID
    -0.66
    aarrggbb
    -0.65
     onCancelled
    -0.65
    POSITIVE LOGITS
     type
    1.02
     kind
    0.97
     sort
    0.86
     method
    0.72
    kind
    0.69
     amount
    0.68
     tipo
    0.67
    type
    0.65
     types
    0.65
     TYPE
    0.63
    Activations Density 4.389%

    No Known Activations