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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11444
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to freedom of speech and expression

    oai_token-act-pair · gemini-2.0-flash

    discussions on freedom of expression

    np_token-act-pair-logits · gpt-4o-mini

    freedom of expression

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    OGND
    -0.78
    ValueStyle
    -0.69
    
    -0.59
    principalColumn
    -0.59
     समीक्षक
    -0.58
    TagHelper
    -0.57
    最快更新
    -0.56
     doInBackground
    -0.56
    balleur
    -0.56
    脚注の使い方
    -0.55
    POSITIVE LOGITS
     expression
    0.62
     hold
    0.53
    tanleria
    0.50
     free
    0.50
     Expression
    0.49
    ")));
    0.48
     holds
    0.48
    ')))
    0.47
    syms
    0.46
    =";
    0.46
    Activations Density 0.892%

    No Known Activations