© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 563
    Prev
    Next
    INDEX
    Explanations

    the letter "A" at the start of texts, and sometimes the word "in."

    oai_token-act-pair · gemini-2.0-flash

    A

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    principalTable
    -0.51
     ?>
    -0.46
    LikeLike
    -0.43
    )];
    -0.42
    #%%
    -0.41
    ']>;
    -0.41
    entibus
    -0.41
    </thead>
    -0.40
    "])
    -0.40
    fromLTRB
    -0.39
    POSITIVE LOGITS
     reaſon
    0.66
     pleaſure
    0.64
     Houſe
    0.60
     houſe
    0.58
    eronau
    0.58
    bit
    0.57
     anſ
    0.57
     Diſ
    0.57
    amir
    0.56
     purpoſe
    0.56
    Activations Density 2.460%

    No Known Activations