INDEX

Explanations

words and phrases that express strong opinions or emotional reactions

oai_token-act-pair · gemini-2.0-flash

Politics/Legal

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

TagMode

-0.81

 يتيمه

-0.73

 NSCoder

-0.71

RegistryLite

-0.69

CloseOperation

-0.66

 CreateTagHelper

-0.66

transQ

-0.64

 Roskov

-0.60

djangoproject

-0.60

ANTLR

-0.59

POSITIVE LOGITS

 stanovnika

0.48

.}}

0.47

 كومونز

0.46

 primary

0.46

 Step

0.45

jstor

0.45

Integration

0.45

 Junge

0.44

jakan

0.44

НИК

0.44

Activations Density 1.410%

words and phrases that express strong opinions or emotional reactions

Politics/Legal

No Comments

No Known Activations