© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13710
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a strong positive emotion

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     дописавши
    -0.81
    UIControlState
    -0.76
    terday
    -0.73
    MigrationBuilder
    -0.69
    CastException
    -0.68
    addContainerGap
    -0.68
    rippa
    -0.68
     <<<<<<<<<<<<<<
    -0.67
     OFDb
    -0.66
    Acest
    -0.66
    POSITIVE LOGITS
     diretamente
    0.45
    وض
    0.42
     groen
    0.40
     belast
    0.40
    ureusement
    0.39
     referrerpolicy
    0.39
    fromnode
    0.39
     barrels
    0.38
     direto
    0.37
     directe
    0.37
    Activations Density 1.060%

    No Known Activations