© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3158
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions frequently used together in phrases

    oai_token-act-pair · gemini-2.0-flash

    academic text

    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
    .
    -1.82
    ".
    -1.27
    ).
    -1.22
    。
    -1.20
    ”.
    -1.18
    }$.
    -1.14
    ].
    -1.12
    ."
    -1.08
    $.
    -1.07
    '.
    -1.07
    POSITIVE LOGITS
     betweenstory
    1.17
     createState
    1.16
    AndEndTag
    1.12
    存于互联网档案馆
    1.10
    featureID
    1.05
    GraphicsUnit
    1.05
     EconPapers
    1.02
     Мексичка
    1.00
    ⓧ
    0.99
    principalColumn
    0.98
    Activations Density 28.013%

    No Known Activations