© 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. 2791
    Prev
    Next
    INDEX
    Explanations

    mentions of having access to something

    oai_token-act-pair · gemini-2.0-flash

    phrases related to access and authorization

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

    access

    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
     joaat
    -0.81
     surla
    -0.77
    oneofs
    -0.77
    TypedDataSet
    -0.76
     CreateTagHelper
    -0.75
     كومونز
    -0.72
    tvguidetime
    -0.69
     onCancelled
    -0.68
    thly
    -0.65
    URLException
    -0.64
    POSITIVE LOGITS
     to
    0.79
     point
    0.61
     points
    0.54
    point
    0.52
     punto
    0.48
    points
    0.44
     Points
    0.43
    Point
    0.42
     POINTS
    0.41
    vnode
    0.41
    Activations Density 3.691%

    No Known Activations