INDEX

Explanations

language describing future possibilities or plans

oai_token-act-pair · gemini-2.0-flash

Related to close

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 AssemblyCompany

-0.54

nitř

-0.48

 صوتيه

-0.47

PerformLayout

-0.47

횟

-0.47

ôles

-0.46

<_>

-0.46

gnancy

-0.45

SupportActionBar

-0.45

POSITIVE LOGITS

 close

3.36

 Close

2.84

close

2.80

Close

2.69

 CLOSE

2.63

CLOSE

2.09

 closer

1.54

 closeness

1.49

closer

1.45

 closeup

1.41

Activations Density 7.054%

language describing future possibilities or plans

Related to close

No Comments

No Known Activations