INDEX

Explanations

tokens within a text about education or that are related to schooling

oai_token-act-pair · gemini-2.0-flash

Code and lists

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

#+#

-0.83

TargetException

-0.73

/>";

-0.71

]--;

-0.68

enumi

-0.68

Tikang

-0.65

>";

-0.62

+");

-0.62

 />";

-0.59

 tartalomajánló

-0.59

POSITIVE LOGITS

 propOrder

0.47

 estimés

0.44

 Mawr

0.44

Сек

0.42

IsContent

0.42

QByteArray

0.41

espèce

0.41

rimi

0.41

Nazionale

0.40

 spotting

0.39

Activations Density 5.961%

tokens within a text about education or that are related to schooling

Code and lists

No Comments

No Known Activations