© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11908
    Prev
    Next
    INDEX
    Explanations

    descriptions of food, flavors, and the experience of eating.

    oai_token-act-pair · gemini-2.0-flash

    flavors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    @[+][
    -0.68
     صوتيه
    -0.63
    medriver
    -0.63
    Tembelea
    -0.60
     فريبيس
    -0.59
    rinfo
    -0.58
    findpost
    -0.58
     Meksiku
    -0.57
    tioners
    -0.57
     Signalez
    -0.57
    POSITIVE LOGITS
     nakalista
    0.57
     gddr
    0.48
     sztu
    0.48
    
    0.48
     apapun
    0.46
     alpina
    0.45
    harusnya
    0.45
     Dulce
    0.45
     Italij
    0.45
     quoique
    0.44
    Activations Density 1.498%

    No Known Activations