© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6137
    Prev
    Next
    INDEX
    Explanations

    words frequently used as prepositions and conjunctions in conversational English

    oai_token-act-pair · gemini-2.0-flash

    determiners and pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ]),
    
    -0.65
     كومونز
    -0.61
    ]**
    -0.59
    ))->
    -0.58
    }`).
    -0.58
    "]);
    
    -0.58
    "]));
    -0.57
    DllImport
    -0.55
    )";
    
    -0.54
    dler
    -0.53
    POSITIVE LOGITS
    the
    1.33
    this
    1.09
    a
    1.06
    its
    1.00
    my
    0.98
    it
    0.97
    their
    0.95
    these
    0.92
    there
    0.91
    your
    0.90
    Activations Density 28.488%

    No Known Activations