© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12016
    Prev
    Next
    INDEX
    Explanations

    the word "it" and words immediately surrounding "it"

    oai_token-act-pair · gemini-2.0-flash

    technical documentation

    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
     rapporti
    -0.54
     inspirasi
    -0.50
     ocasião
    -0.47
     precedenti
    -0.46
     singoli
    -0.45
     arbres
    -0.44
     culoare
    -0.44
     kepad
    -0.42
     OMITTED
    -0.42
     responsabilità
    -0.42
    POSITIVE LOGITS
    windowFixed
    0.77
     ब्रेकडाउन
    0.71
    ChildScrollView
    0.70
     Normdatei
    0.67
     ―――――
    0.63
    AutoScaleMode
    0.60
     ――――――――
    0.60
    TintMode
    0.60
    AnchorStyles
    0.59
     hyaluronic
    0.59
    Activations Density 2.230%

    No Known Activations