© 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. 1112
    Prev
    Next
    INDEX
    Explanations

    past participles following "I've", "you've", or "never"

    oai_token-act-pair · gemini-2.0-flash

    experienced, seen, or heard

    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
    selig
    -0.56
    findpost
    -0.56
     Conducted
    -0.56
    principalTable
    -0.52
    sees
    -0.51
     betweenstory
    -0.51
    >{@
    -0.51
    évaluateur
    -0.51
    ning
    -0.50
    kaido
    -0.50
    POSITIVE LOGITS
     EconPapers
    0.73
    клопе
    0.56
    ContentAlignment
    0.54
     يتيمه
    0.54
    onomía
    0.49
     iNdEx
    0.48
     kaarangay
    0.47
     coronation
    0.46
    esModule
    0.46
    Portale
    0.46
    Activations Density 5.622%

    No Known Activations