© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1388
    Prev
    Next
    INDEX
    Explanations

    phrases that evaluate a situation or state a constraint.

    oai_token-act-pair · gemini-2.0-flash

    also

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    DidLoad
    -0.52
    BufferException
    -0.51
     comigo
    -0.50
     विश्वसनीयता
    -0.49
     Weeknd
    -0.48
     TestBed
    -0.47
    λαι
    -0.47
     ISNI
    -0.47
    voltaic
    -0.46
     Agencies
    -0.46
    POSITIVE LOGITS
    μερα
    0.50
    __':
    0.50
    دانشنامهٔ
    0.48
     static
    0.48
    MigrationBuilder
    0.47
     <<<<<<<<<<<<<<
    0.47
    انجليز
    0.47
     rowspan
    0.47
    }();
    0.46
    stry
    0.46
    Activations Density 2.563%

    No Known Activations