© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11738
    Prev
    Next
    INDEX
    Explanations

    phrases that encourage someone to identify with a character, idea, or event

    oai_token-act-pair · gemini-2.0-flash

    entertainment/media

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    twimg
    -0.57
     CWE
    -0.55
     confirmed
    -0.55
     confirm
    -0.53
    delwed
    -0.52
    يميديا
    -0.52
    Confirm
    -0.51
    ähig
    -0.51
    Boas
    -0.51
     contem
    -0.51
    POSITIVE LOGITS
    الإنجليزية
    0.61
     BoxFit
    0.59
     tartalomajánló
    0.57
    ंदीखरीदारी
    0.55
    SequentialGroup
    0.54
     onPostExecute
    0.54
    granate
    0.54
    BeginContext
    0.54
     مشين
    0.53
    假日
    0.52
    Activations Density 3.066%

    No Known Activations