INDEX

Explanations

code snippets related to testing, particularly in PHP

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

ब्द

-0.49

CDCl

-0.45

 poffible

-0.45

 fufficient

-0.44

 profitably

-0.43

 reafon

-0.42

 strategic

-0.42

 adults

-0.42

 uſed

-0.42

 indoor

-0.41

POSITIVE LOGITS

$\\

0.84

0.81

,\\

0.78

?\\

0.76

}$\\

0.74

 Audiodateien

0.71

\\

0.71

)$\\

0.68

;\\

0.66

{$

0.65

Activations Density 10.424%

code snippets related to testing, particularly in PHP

code snippets

No Comments

No Known Activations