© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 2164
    Prev
    Next
    INDEX
    Explanations

    German sentences using modal verbs, especially with multiple nested modal verbs

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks and sentence boundaries

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

    punctuation

    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
    UserScript
    -1.03
    >`;
    -0.95
    ]));
    
    -0.94
     itſelf
    -0.91
     myſelf
    -0.91
    }))
    
    -0.90
     poffible
    -0.86
     ErrIntOverflow
    -0.85
    AsUp
    -0.85
    Datuak
    -0.85
    POSITIVE LOGITS
    .
    0.81
    ,
    0.63
     -
    0.49
    :
    0.49
    !
    0.48
     –
    0.41
     ,
    0.41
     
    0.40
     and
    0.39
     (
    0.38
    Activations Density 1.734%

    No Known Activations