© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6718
    Prev
    Next
    INDEX
    Explanations

    common prefixes and suffixes in words, particularly those related to measurement, location, or direction

    oai_token-act-pair · gemini-2.0-flash

    Ratios, rates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     nakalista
    -1.28
    <bos>
    -1.26
     disambiguazione
    -1.25
    tagHelperRunner
    -1.16
    verwijspagina
    -1.06
    "]);
    -1.01
    ]));
    -0.97
    )");
    -0.96
    "));
    -0.90
    rungsseite
    -0.89
    POSITIVE LOGITS
     Diſ
    1.16
     purpoſe
    1.13
     himſelf
    1.09
     houſe
    1.09
     ſen
    1.06
     pleaſure
    1.02
     ſta
    1.02
     Monfieur
    1.02
     Theſe
    1.02
     Conſ
    1.01
    Activations Density 4.961%

    No Known Activations