INDEX

Explanations

the word "that" used as a conjunction following "in", or the word "sense".

oai_token-act-pair · gemini-2.0-flash

sense that

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

findpost

-0.99

 nahilalakip

-0.79

<bos>

-0.69

 bezeichneter

-0.68

 ModelExpression

-0.65

ScopeManager

-0.65

 ProtoMessage

-0.62

expandindo

-0.62

 AssemblyProduct

-0.62

 الرياضيه

-0.62

POSITIVE LOGITS

 they

0.47

Rø

0.43

iverr

0.43

 [''],

0.41

Need

0.41

érien

0.40

{{$

0.40

">{{$

0.40

 mian

0.39

 whenever

0.38

Activations Density 2.439%

the word "that" used as a conjunction following "in", or the word "sense".

sense that

No Comments

No Known Activations