© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12388
    Prev
    Next
    INDEX
    Explanations

    phrases related to staying informed or connected

    oai_token-act-pair · gemini-2.0-flash

    staying informed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    IntoConstraints
    -1.09
    +#+#
    -1.01
     EconPapers
    -0.98
    DockStyle
    -0.90
    MessageOf
    -0.88
    encodeWith
    -0.85
    BagConstraints
    -0.84
    __':
    -0.82
    +#+
    -0.81
     GenerationType
    -0.81
    POSITIVE LOGITS
    ed
    0.43
    endy
    0.42
     in
    0.42
    점
    0.42
    in
    0.41
     sk
    0.40
     let
    0.40
    uli
    0.39
     h
    0.38
     die
    0.38
    Activations Density 0.749%

    No Known Activations