Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 6934
    Prev
    Next
    INDEX
    Explanations

    mentions of nightstands or bedside tables

    oai_token-act-pair · gemini-2.0-flash

    table

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     []:
    -0.59
    HostException
    -0.56
    émie
    -0.54
    ynchronously
    -0.53
    atoon
    -0.52
    tvguidetime
    -0.52
    cinta
    -0.50
     '{@
    -0.49
    ]")]
    -0.49
    Programme
    -0.48
    POSITIVE LOGITS
     table
    1.13
     tables
    1.04
     Table
    0.90
    table
    0.88
     Tables
    0.84
    Table
    0.82
    テーブル
    0.81
     TABLES
    0.81
     TABLE
    0.80
    TABLE
    0.78
    Activations Density 0.943%

    No Known Activations