INDEX

Explanations

java code snippets

oai_token-act-pair · gemini-2.0-flash

code snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

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

]();

-0.57

».

-0.50

itively

-0.50

„

-0.49

();?>

-0.48

′

-0.47

().

-0.47

"،

-0.47

 rocked

-0.47

POSITIVE LOGITS

endphp

0.57

 Sell

0.52

↵↵

0.52

croll

0.52

 Settle

0.52

 BorderRadius

0.51

 Stop

0.50

net

0.49

 doInBackground

0.47

 Upload

0.47

Activations Density 3.301%

java code snippets

code snippets

No Comments

No Known Activations