INDEX

Explanations

punctuation, in particular commas, and/or the word "the".

oai_token-act-pair · gemini-2.0-flash

comma

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

so

-0.44

amp

-0.36

Hentet

-0.35

terraform

-0.34

us

-0.34

Weil

-0.34

 DataLoader

-0.33

 fact

-0.33

itorio

-0.33

deed

-0.33

POSITIVE LOGITS

+#+#

0.93

XmlAccessType

0.88

InputTagHelper

0.87

tagHelperRunner

0.82

 متعلقه

0.81

 gynhyrchwyd

0.80

we

0.78

 المعيارى

0.77

 they

0.76

AndEndTag

0.71

Activations Density 5.892%

punctuation, in particular commas, and/or the word "the".

comma

No Comments

No Known Activations