INDEX

Explanations

code snippets, especially bash scripts and variable assignments.

oai_token-act-pair · gemini-2.0-flash

symbols

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

 externi

-0.75

IUrlHelper

-0.62

 Мексичка

-0.61

 beginnetje

-0.60

EndContext

-0.55

errHandler

-0.55

raborty

-0.55

CompilerServices

-0.55

readAs

-0.55

الحياه

-0.54

POSITIVE LOGITS

1.28

']=

0.90

}=

0.87

"]=

0.86

.=

0.79

)=

0.76

]=

0.75

"=

0.68

,=

0.66

}}=

0.66

Activations Density 7.639%

code snippets, especially bash scripts and variable assignments.

symbols

No Comments

No Known Activations