INDEX

Explanations

uses of "to" as an infinitive

oai_token-act-pair · gemini-2.0-flash

Suggestions

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

SequentialGroup

-0.77

spesies

-0.64

NOPQRST

-0.64

 szóci

-0.64

 AssemblyCulture

-0.63

berdayakan

-0.61

+'</

-0.60

ंदीखरीदारी

-0.60

 kérdés

-0.60

Geplaatst

-0.59

POSITIVE LOGITS

regate

0.53

 stock

0.49

curities

0.47

 chat

0.46

::$_

0.45

 uLocal

0.45

 check

0.45

 escape

0.44

 "..\..\

0.44

SEP

0.44

Activations Density 1.508%

uses of "to" as an infinitive

Suggestions

No Comments

No Known Activations