INDEX

Explanations

sentence boundaries, conjunctions, and references to studies and papers

oai_token-act-pair · gemini-2.0-flash

period

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

 autorytatywna

-1.13

Rhestr

-0.84

 resourceCulture

-0.82

NameInMap

-0.81

 дописавши

-0.78

CodeAttribute

-0.77

 transférez

-0.76

 ddelweddau

-0.75

 nahilalakip

-0.74

 AssemblyCulture

-0.73

POSITIVE LOGITS

 zatem

0.49

 therefore

0.48

 Therefore

0.47

从中

0.47

mény

0.45

 giudi

0.45

 anyway

0.44

 accordingly

0.44

 الوطنيه

0.43

 därför

0.43

Activations Density 1.823%

sentence boundaries, conjunctions, and references to studies and papers

period

No Comments

No Known Activations