© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15256
    Prev
    Next
    INDEX
    Explanations

    the word "positive"

    oai_token-act-pair · gemini-2.0-flash

    positive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     of
    -0.82
    ing
    -0.69
    ↵
    -0.69
     present
    -0.67
     "
    -0.67
     her
    -0.65
     total
    -0.63
     position
    -0.60
     '
    -0.59
     r
    -0.56
    POSITIVE LOGITS
     Réponses
    1.30
     Prussia
    1.09
     hierogly
    1.07
     titolata
    1.05
     Phry
    1.04
    ConstraintMaker
    1.03
     Româ
    1.03
     sogni
    1.02
     pouvoit
    1.02
     uș
    1.02
    Activations Density 1.100%

    No Known Activations