INDEX

Explanations

words related to testimony, software development, sports and doing/choosing.

oai_token-act-pair · gemini-2.0-flash

doing

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

 للمعارف

-0.60

andescent

-0.57

poptosis

-0.57

 }^{[

-0.56

FunctionFlags

-0.54

formatics

-0.54

Дереккөздер

-0.54

beled

-0.53

 colorful

-0.52

 ModelAndView

-0.52

POSITIVE LOGITS

FormTagHelper

0.66

mybatisplus

0.61

 Normdatei

0.59

ioutil

0.56

UrlResolution

0.54

 BoxFit

0.54

 conti

0.52

GEBURTSDATUM

0.48

:✨

0.48

Rüyada

0.47

Activations Density 17.983%

words related to testimony, software development, sports and doing/choosing.

doing

No Comments

No Known Activations