INDEX

Explanations

forms of the verb "implicate" and "involve."

oai_token-act-pair · gemini-2.0-flash

implicate

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 HasFactory

-0.54

uteen

-0.54

 nhật

-0.50

numerusform

-0.49

erar

-0.48

 Verv

-0.47

 aufge

-0.47

ørs

-0.47

غی

-0.47

weichen

-0.46

POSITIVE LOGITS

 involved

1.64

involved

1.63

 Involved

1.52

 involve

1.36

 involvement

1.29

 INVOLVED

1.29

 Involvement

1.17

 INVOL

1.10

 involuc

1.08

 involves

1.07

Activations Density 0.521%

forms of the verb "implicate" and "involve."

implicate

No Comments

No Known Activations