INDEX

Explanations

words indicating negativity with some focus on the word "steady," and possibly numbers related to stability.

oai_token-act-pair · gemini-2.0-flash

extremes

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

-0.67

-0.58

-0.56

ato

-0.56

do

-0.54

Wir

-0.54

us

-0.53

ich

-0.53

 realise

-0.53

lib

-0.52

POSITIVE LOGITS

rungsseite

1.41

GEBURTSDATUM

1.12

 CreateTagHelper

1.05

 snippetHide

1.05

 مشين

1.02

>//

1.00

istoitu

0.99

VersionUID

0.97

hematical

0.94

 händer

0.94

Activations Density 2.105%

words indicating negativity with some focus on the word "steady," and possibly numbers related to stability.

extremes

No Comments

No Known Activations