© 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. 10847
    Prev
    Next
    INDEX
    Explanations

    phrases related to food quality, ingredients and freshness

    oai_token-act-pair · gemini-2.0-flash

    fresh

    np_max-act-logits · 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
     fresh
    -3.19
    fresh
    -3.06
    Fresh
    -3.00
     Fresh
    -3.00
     FRESH
    -2.75
    FRESH
    -2.41
     fresher
    -2.39
     freshest
    -2.39
     freshness
    -2.33
     frischen
    -2.23
    POSITIVE LOGITS
    ers
    0.49
     betweenstory
    0.48
    Bibliografia
    0.48
    ingly
    0.45
    Референце
    0.42
    tingly
    0.42
    सो
    0.41
    Linki
    0.41
    SizeF
    0.40
    CPP
    0.40
    Activations Density 1.242%

    No Known Activations