© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 562
    Prev
    Next
    INDEX
    Explanations

    text describing the history and ingredients of a Philly cheesesteak sandwich

    oai_token-act-pair · gemini-2.0-flash

    food history/description

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ItemBackground
    -0.67
     HasFactory
    -0.60
    PerformLayout
    -0.57
    ernalia
    -0.56
    PropertyGroup
    -0.55
     BrowserModule
    -0.53
     SafeMath
    -0.52
    saraba
    -0.51
     Nieto
    -0.50
     خارجية
    -0.50
    POSITIVE LOGITS
     endforeach
    0.57
    QMetaType
    0.54
    ]")]
    0.54
     odkazy
    0.53
    兵衛
    0.51
    TagMode
    0.51
    endwhile
    0.50
    ArgsConstructor
    0.49
    hassee
    0.49
    interopRequire
    0.48
    Activations Density 0.791%

    No Known Activations