© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13778
    Prev
    Next
    INDEX
    Explanations

    subjective language, opinions and feelings.

    oai_token-act-pair · gemini-2.0-flash

    opinions/thoughts/self-reference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    Abitanti
    -0.58
    CURLOPT
    -0.56
     [*]
    -0.53
     QtGui
    -0.52
    enumii
    -0.52
     handleMessage
    -0.52
    帖最后由
    -0.52
     Such
    -0.50
    SizeMode
    -0.48
    +:+
    -0.48
    POSITIVE LOGITS
    دانشنامهٔ
    0.61
     estekak
    0.57
    abestanden
    0.56
     ourselves
    0.55
     our
    0.54
     InputDecoration
    0.53
     للمعارف
    0.52
    脚注の使い方
    0.51
    felizmente
    0.51
    rungsseite
    0.50
    Activations Density 5.450%

    No Known Activations