INDEX

Explanations

words and symbols commonly seen in programming languages and math equations

oai_token-act-pair · gemini-2.0-flash

Code-related terms

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 Value

-1.42

 value

-1.42

Value

-1.38

value

-1.30

 VALUE

-1.27

 Values

-1.26

 values

-1.19

VALUE

-1.17

 valeur

-1.15

值

-1.13

POSITIVE LOGITS

sizeCache

0.47

 natale

0.47

ništvo

0.46

драт

0.45

 incident

0.45

Inc

0.45

 Benth

0.45

 tölt

0.43

};*/

0.43

LinkId

0.42

Activations Density 1.843%

words and symbols commonly seen in programming languages and math equations

Code-related terms

No Comments

No Known Activations