© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 298
    Prev
    Next
    INDEX
    Explanations

    adjectives describing food

    oai_token-act-pair · gemini-2.0-flash

    food and cuisine

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Music
    -1.55
    Music
    -1.48
     music
    -1.48
    music
    -1.39
     MUSIC
    -1.33
    MUSIC
    -1.25
     Musik
    -1.23
     musique
    -1.19
    Musik
    -1.14
     música
    -1.06
    POSITIVE LOGITS
    ScopeManager
    0.78
    SBATCH
    0.69
    jface
    0.69
    CloseOperation
    0.65
    sidemargin
    0.64
    AutoScaleMode
    0.61
    tagHelperRunner
    0.60
    TagHelpers
    0.59
     endblock
    0.58
    RuleContext
    0.57
    Activations Density 2.947%

    No Known Activations