© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10719
    Prev
    Next
    INDEX
    Explanations

    discussion of machining, particularly the functioning of hobbing machines

    oai_token-act-pair · gemini-2.0-flash

    hob

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     initComponents
    -0.60
    
    -0.55
    copg
    -0.54
     SqlConnection
    -0.53
    ReferenceEquals
    -0.51
    NewUrlParser
    -0.49
    Brainz
    -0.47
     Damon
    -0.47
    DatabaseError
    -0.46
    BuildContext
    -0.46
    POSITIVE LOGITS
    Koordinaten
    0.63
     morgon
    0.60
     estekak
    0.55
    DockStyle
    0.55
     profundas
    0.53
    AutoScaleMode
    0.53
     ModelExpression
    0.53
     tör
    0.51
    FTFY
    0.51
     atât
    0.50
    Activations Density 0.197%

    No Known Activations