INDEX

Explanations

language related to real estate

oai_token-act-pair · gemini-2.0-flash

plot

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

tvguidetime

-0.59

مراجع

-0.56

لينكات

-0.55

peed

-0.47

Références

-0.46

 rapat

-0.46

Šaltiniai

-0.45

Tour

-0.45

 Tour

-0.45

 teto

-0.44

POSITIVE LOGITS

 plot

1.23

 plots

1.20

 Plots

1.10

plot

1.05

 Plot

1.02

Plots

1.02

plots

0.99

Plot

0.99

PLOT

0.98

 PLOT

0.98

Activations Density 1.163%

language related to real estate

plot

No Comments

No Known Activations