INDEX

Explanations

the word "per" along with numbers and other similar words

oai_token-act-pair · gemini-2.0-flash

per

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

per

-2.53

Per

-2.33

per

-2.14

Per

-2.13

PER

-1.82

PER

-1.65

 peri

-0.94

PerPage

-0.94

パー

-0.90

PerSecond

-0.88

POSITIVE LOGITS

 désolés

0.65

 protoimpl

0.64

addContainerGap

0.62

 CreateTagHelper

0.54

IActionResult

0.54

localScale

0.53

Biographie

0.52

 <<<<<<<<<<<<<<

0.51

 resourceCulture

0.51

ContentAsync

0.50

Activations Density 2.855%

the word "per" along with numbers and other similar words

per

No Comments

No Known Activations