© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11625
    Prev
    Next
    INDEX
    Explanations

    a variety of words related to podcasts, video production, and discussion

    oai_token-act-pair · gemini-2.0-flash

    audio/video content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     StringTokenizer
    -0.67
    PerformLayout
    -0.65
    bootstrapcdn
    -0.64
    CPtr
    -0.63
     ModelExpression
    -0.62
    atguigu
    -0.62
    principalTable
    -0.60
    EClass
    -0.59
     resourceCulture
    -0.57
    GHIJKLM
    -0.56
    POSITIVE LOGITS
     ISNI
    0.56
    ก่
    0.53
     CommandType
    0.50
     isolato
    0.50
     arşivlendi
    0.49
     suivie
    0.48
     Далее
    0.48
     mukana
    0.47
     csin
    0.47
    <bos>
    0.46
    Activations Density 0.926%

    No Known Activations