INDEX

Explanations

words and phrases that describe feelings

oai_token-act-pair · gemini-2.0-flash

so

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

so

-0.65

så

-0.59

so

-0.54

 raisonnable

-0.50

 begitu

-0.50

Så

-0.49

ⓧ

-0.49

So

-0.47

Så

-0.47

 così

-0.46

POSITIVE LOGITS

mybatisplus

0.77

NewUrlParser

0.70

NUMX

0.69

VersionUID

0.65

ITUD

0.64

الدراسه

0.64

Tikang

0.62



0.61

ürzen

0.60

انگلیسی

0.60

Activations Density 1.928%

words and phrases that describe feelings

so

No Comments

No Known Activations