© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6305
    Prev
    Next
    INDEX
    Explanations

    small connecting words or prepositions in relation to the word "the"

    oai_token-act-pair · gemini-2.0-flash

    words related to the setting of a crime scene

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

    rooms in a house

    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
     insuffisamment
    -0.64
    wpi
    -0.54
    ereum
    -0.54
     بيها
    -0.54
     виправивши
    -0.50
    NUMX
    -0.49
    -------
    -0.49
     barbacoa
    -0.49
    ]")]
    -0.47
    Letra
    -0.47
    POSITIVE LOGITS
    aarrggbb
    0.57
    great
    0.51
     great
    0.50
     autorytatywna
    0.50
     GREAT
    0.49
     formal
    0.49
     host
    0.49
    🥞
    0.49
    "]).
    0.49
    اریخ
    0.48
    Activations Density 0.380%

    No Known Activations