INDEX

Explanations

the word and followed by a high number.

oai_token-act-pair · gemini-2.0-flash

foreign language terms or phrases

np_token-act-pair-logits · gpt-4o-mini

and

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 архивлан

-0.46

MAC

-0.41

때

-0.40

 >=",

-0.40

thi

-0.39

each

-0.38

pegno

-0.38

⇑

-0.38

Mac

-0.38

POSITIVE LOGITS

findpost

0.77

 résister

0.69

 eenig

0.69

 ainfi

0.69

 zoude

0.68

ArgsConstructor

0.67

 hâte

0.67

ScopeManager

0.65

 stiefel

0.64

 tiegħek

0.64

Activations Density 21.694%

the word and followed by a high number.

foreign language terms or phrases

and

No Comments

No Known Activations