© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15846
    Prev
    Next
    INDEX
    Explanations

    the verb "point" in its various forms, often followed by prepositions

    oai_token-act-pair · gemini-2.0-flash

    point

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    contentPane
    -0.46
    icho
    -0.42
    RefreshLayout
    -0.39
     MatDialog
    -0.39
     multer
    -0.39
    TagMode
    -0.39
    uesia
    -0.39
     gắng
    -0.39
    istad
    -0.39
    cookieParser
    -0.39
    POSITIVE LOGITS
     ujednoznacz
    0.90
     typelib
    0.86
     pointing
    0.85
    IntoConstraints
    0.82
    ########.
    0.81
     saites
    0.75
     oprot
    0.73
    Enllaces
    0.73
     pointed
    0.73
    INCREF
    0.72
    Activations Density 1.374%

    No Known Activations